Temporal boundary of wildfire incidents

Abstract

A method, system, and apparatus, including a computer program encoded on a computer storage medium, for generating a time range of a fire. In some implementations, a server obtains a date that a fire started in a region. The server obtains satellite imagery of the region prior to the date that the fire started. The server generates a first statistical distribution from the satellite imagery. The server uses the first statistical distribution to determine a start date of the fire. The server obtains second satellite imagery of the region prior to the start date and after the start date. The server selects a second set of images from the second satellite imagery prior to the start date. The server generates a second statistical distribution from the second set of images. The server uses the second statistical distribution to determine an end date of the fire. The server provides the start date and end date for output.

Description

Technical Field

[0001] This specification generally relates to computer simulations, and one particular implementation relates to generating a time range of wildfires using statistical distributions and satellite imagery.

Background Art

[0002] Wildfires can include forest fires, wildland fires, rural fires, etc., and can occur in various geographical regions. A wildfire can originate in one geographical area and spread to another geographical area over a period of time. Wildfires can be caused by factors such as climate, vegetation, and even human activities, to name a few.

Summary of the Invention

[0003] The techniques described in this specification generate a time range of historical wildfires across a geographical area. In particular, a server can generate a time range that includes a start date and an end date of a wildfire given its spatial boundaries in a geographical area, and the dates on which the wildfire occurred in the geographical area. The start date corresponds to the day the wildfire occurred. The end date corresponds to the day the wildfire ended.

[0004] Techniques for generating the time range of a wildfire event are important because this range can be utilized and needed for other purposes. For example, a server can provide the time range as training data for machine learning or another machine learning model pipeline to predict the length of a fire. In another example, the server can provide the generated time range to a graphical user interface that can display the spread and length of the wildfire. In other examples, the server can also provide the generated time range to a process that attempts to identify the start date of an ongoing wildfire. In other examples, an individual may want to analyze other sensor data before and after a wildfire occurs. Automatically detecting the start and end dates of a wildfire can help complete these investigations. For example, an analyst may need the time boundaries of a wildfire while attempting to estimate the annual tree mortality in a specific area due to the wildfire.

[0005] In some implementations, the server can receive the date on which a wildfire occurred within a geographic area. This date can be the start date, end date, or any date between the start and end dates. The geographic area can be defined, for example, by location data that can include longitude and latitude coordinates and the area or region surrounding these location coordinates.

[0006] The server can communicate with a satellite image database to obtain satellite images of various geographic areas. The satellite image database can store satellite images of various geographic areas of the Earth over various periods, including infrared and other satellite data. The satellite images can also include other processed satellite image products, such as MODIS MCD45A1, which includes per-pixel burn and quality assurance information. The satellite image database can index the satellite images by several factors, such as location data, time, date, and the boundary regions of the geographic area.

[0007] The server can identify and retrieve satellite images using location data associated with a geographic area and an input date on which a fire occurred. In particular, the server can provide the location data and the input date to a satellite image database and receive satellite images from a period before the provided input date. In some implementations, the server can provide the location data and the input date to the satellite image database and receive satellite images from periods before and after the provided input date.

[0008] In some implementations, the server can generate a statistical distribution based on the acquired satellite images of a specific geographic area from a period before the input date. As further described below, the server can generate a baseline of satellite images corresponding to the period before the input date, and each image within the baseline shows the geographic area over a defined period. When the server generates a statistical distribution, the server can identify the start date of the wildfire.

[0009] In some implementations, the server can determine the start date of the wildfire by comparing the satellite image with the statistical distribution. The server can acquire a satellite image corresponding to a period of the geographic area before the input date, for example, a period of the geographic area three months before the input date. Three months before the input date is selected to ensure that the statistical distribution has no and does not contain fire pixels. Further, the server can filter the satellite image within the minimum known perimeter of the wildfire. This will be further described below. The server can compare the satellite image with the statistical distribution to identify the start date of the wildfire.

[0010] In some implementations, the server can determine the end date of the wildfire by generating additional statistical distributions. The server can generate a second statistical distribution based on the acquired satellite images of a specific geographic area from a period before the determined start date. For example, the server filters the acquired satellite images within the latest known perimeter of the wildfire within the geographic area. As will be further described below, the server can improve the accuracy of identifying the end date by generating additional statistical distributions using the determined start date instead of the provided input date. When generating the second statistical distribution, the server can generate another baseline of satellite images corresponding to the period before the determined start date, and each image within the baseline shows the geographic area over a defined period. When the server generates the second statistical distribution, the server can identify the end date of the wildfire.

[0011] In some implementations, the server can determine the end date of the wildfire by comparing the satellite images with the second statistical distribution. The server can acquire satellite images corresponding to the period of the geographic area after the determined start date. The selection of satellite images after the period of the determined start date is necessary to determine the end date, and the selection of satellite images before the period of the provided input date is necessary to determine the start date.

[0012] The server can then provide, for output, the time range of the wildfire, e.g., the determined start date and end date of the wildfire. The output can be for a connected client device, display, or one or more other applications.

[0013] In one general aspect, the method is performed by a server. The method includes the server obtaining a date on which a fire occurred within a geographic area, the server obtaining a first satellite image of the geographic area prior to the date on which the fire occurred within the geographic area, the server selecting a first set of images from the first satellite image prior to the date on which the fire occurred within the geographic area, the server generating a first statistical distribution from the first set of images, the server determining a start date of the fire based on a comparison of the first satellite image and the first statistical distribution, the server obtaining a second satellite image of the geographic area before and after the determined start date on which the fire occurred within the geographic area, the server selecting a second set of images from the second satellite image before the start date on which the fire occurred within the geographic area, wherein the amount of the second set of images is less than the amount of the first set of images, the server generating a second statistical distribution from the second set of images before the start date on which the fire occurred within the geographic area, the server determining an end date of the fire based on a comparison of the second satellite image that occurred after the start date and the second statistical distribution, and the server providing a range including the start date of the fire and the end date of the fire within the geographic area for output by the server.

[0014] This and other embodiments and other aspects of the disclosure include corresponding systems, devices, and computer programs encoded on a computer storage device and configured to perform the actions of this method. One or more computer systems can be configured in this way by software, firmware, hardware, or combinations thereof installed on the system that cause the system to perform actions during operation. One or more computer programs can be configured in this way by virtue of having instructions that, when executed by a data processing device, cause the device to perform actions.

[0015] The above and other embodiments can each optionally include one or more of the following features, alone or in combination. For example, one embodiment includes a combination of all of the following features.

[0016] In some implementations, the method includes the server obtaining a location describing the geographic area and the server obtaining a date on which a fire occurred within the geographic area, where the date can correspond to the start date of the fire, the end date of the fire, or another date within the range.

[0017] In some implementations, the method includes the server providing a location describing the geographic area where the fire occurred and the date on which the fire occurred to a satellite image database, and in response to providing the location and date, the server obtaining a first satellite image of the geographic area from a period prior to the date.

[0018] In some implementations, the method includes the server identifying a period for generating a first statistical distribution, where the period corresponds to a period prior to the date, the server selecting a first set of images from the first satellite image based on the period, the server determining an indication of whether one or more pixels from the selected first set of images indicate a fire, and the server adjusting the selected first set of images by comparing one or more pixels indicating a fire to a threshold.

[0019] In some implementations, the method includes generating a first statistical distribution from a first set of images, by the server, in response to adjusting the selected first set of images, by the server determining, for each day of the first set of images, the number of pixels indicating a fire, by the server determining the average of the number of pixels indicating a fire for each day of the first set of images, and by the server generating the first statistical distribution by setting the determined average to one or more parameters.

[0020] In some implementations, the method includes determining a start date of a fire based on a comparison of a first satellite image and the first statistical distribution, by the server identifying a satellite image from the first satellite images corresponding to days prior to the date on which the fire occurred, by the server determining, from the identified satellite image of the day, the number of pixels that appear to indicate a fire, by the server generating, based on the first statistical distribution and the determined number of pixels that appear to indicate a fire, a likelihood that the satellite image from the first satellite images contains an indication of a fire, by the server comparing the likelihood to a threshold, and in response to determining that the likelihood does not exceed the threshold, by the server obtaining another satellite image from the first satellite images corresponding to another day prior to the date on which the fire occurred to determine the start date.

[0021] In some implementations, in response to determining that the likelihood for a particular day exceeds a threshold, the method includes the server obtaining additional satellite images for a predetermined number of days prior to the particular day, determining, for each day of the predetermined number of days, the number of active fire pixels from the additional satellite image for that day by the server, generating, by the server, a likelihood that the additional satellite image for that day does not contain an indication based on a first statistical distribution and the determined number of pixels that appear to indicate a fire, and determining, by the server, that the day corresponding to the identified satellite image corresponds to the start date of the fire in response to determining that each day of the predetermined number of days does not indicate a fire.

[0022] In some implementations, the method includes the server providing, to a satellite image database, a location describing the geographic area where the fire occurred and a start date on which the fire occurred, and in response to providing the location and start date, obtaining, by the server, a second satellite image of the geographic area from periods before and after the start date.

[0023] In some implementations, selecting a second set of images from a second satellite image of the geographic area prior to the start date of the fire in the geographic area, where the amount of the second set of images is less than the amount of the first set of images, includes the server identifying a period for generating a second statistical distribution, where the period corresponds to a period prior to the start date, selecting, by the server, a second set of images from the second satellite image based on the period, determining, by the server, an indication as to whether one or more pixels from the selected second set of images indicate a fire, and adjusting, by the server, the selected second set of images by comparing one or more pixels indicating a fire to a threshold.

[0024] In some implementations, the method includes generating a second statistical distribution from a second set of images prior to the start date on which a fire occurred within a geographic region, in response to adjusting the second set of selected images, by the server, setting one or more parameters of the second statistical distribution, by the server, determining the number of pixels indicating a fire on each day of the second set of images, by the server, determining an average of the number of pixels indicating a fire on each day of the second set of images, and by the server, generating the second statistical distribution by setting the determined average to the one or more parameters.

[0025] In some implementations, the method includes determining an end date of a fire based on a comparison of a second satellite image and the second statistical distribution that occurred after the start date, by the server, identifying a satellite image from the second satellite images corresponding to dates after the start date, by the server, determining the number of pixels that appear to indicate a fire from the identified satellite image of the day, by the server, generating a likelihood that the satellite image from the second satellite images includes an indication of a fire based on the second statistical distribution and the determined number of pixels that appear to indicate a fire, by the server, comparing the likelihood to a threshold, and in response to determining that the likelihood exceeds the threshold, by the server, obtaining another satellite image from a first satellite image corresponding to another date after the date on which the fire occurred to determine the end date.

[0026] In some implementations, in response to determining that the likelihood for a particular day exceeds a threshold, the method includes the server obtaining additional satellite images for a predetermined number of days after the particular day, determining, for each day of the predetermined number of days, the number of pixels from the additional satellite image for that day by the server, generating, by the server, a likelihood that the additional satellite image for that day does not contain an indication based on a second statistical distribution and the determined number of pixels that appear to indicate a fire, and determining, by the server, that the day corresponding to the identified satellite image corresponds to an end day of a fire in response to determining that each day of the predetermined number of days does not indicate a fire.

[0027] In some implementations, the method includes the first and second statistical distributions being different Poisson distributions.

[0028] Details of one or more embodiments of the subject matter of this specification are set forth in the accompanying drawings and the following description. Other features, aspects, and advantages of the subject matter will become apparent from the description, the drawings, and the claims.

Brief Description of the Drawings

[0029]

Figure 1

Figure 2A

Figure 2B

Figure 3

[0030] Like reference numerals and designations in the various drawings indicate like elements. The components, their connections and relationships, and their functions shown herein are by way of example only and are not intended to limit the implementations described and / or claimed in this specification.

DETAILED DESCRIPTION OF THE INVENTION

[0031] FIG. 1 is a block diagram showing an example of a system 100 for generating a time range of a wildfire. The system 100 includes an image server system 102, a satellite image database 104, a time database 106, and a spatial database 108. The system 100 also includes a monitor 126 connected to the image server system 102 to display and enable a user to interact with the image server system 102. Briefly, the system 100 can generate a time range of a wildfire identified from the date on which the wildfire occurred and the corresponding location of the wildfire. The system 100 can generate a plurality of statistical distributions and compare the acquired satellite images with the generated statistical distributions to identify the time range of the wildfire, such as the start date and the end date.

[0032] Typically, the system 100 attempts to generate a time range of a wildfire because the start date and end date of the wildfire are often missing from the database storing the fire information. By generating and storing this information, the system 100 can add to and improve the overall modeling and monitoring of wildfires. This information can also be useful for various wildfire applications, as described below.

[0033] In some implementations, the image server system 102 can include one or more servers or computers connected locally or via a network. The system 100 can include, for example, a local network, a Wi-Fi network, an intranet, an Internet connection, a Bluetooth connection, or any other connection that enables the image server system 102 to communicate with various databases and various computers, for example, to send and receive. FIG. 1 shows various operations in steps (A) - (J) that can be performed in the order shown or in another order.

[0034] The image server system 102 can also communicate with satellites via a satellite network. The satellites can capture media of geographical regions of the Earth, for example, images and videos. The image server system 102 can communicate with the satellites to request and receive captured media of various geographical regions of the Earth. This is further described below.

[0035] In some implementations, the satellite image database 104 can include one or more databases that store satellite images showing one or more geographical regions of the Earth. The satellite images can include high-quality satellite images, medium-quality satellite images, noisy satellite images, and other satellite images. Further, the satellite image database 104 can store satellite images showing one or more geographical regions of the Earth over a period of time. For example, the satellite images can include media of a specific geographical region of the Earth, such as images and videos, over the past one year, five years, ten years, fifteen years, or more from the current time. The satellite image database 104 can include satellite images for each day over a past period. In some cases, the satellite image database 104 can include multiple images or multiple videos from each day of a geographical region.

[0036] The satellite image database 104 can store satellite media of multiple geographical regions of the Earth over various periods. For example, the satellite image database 104 can store satellite images from geographical region 1 to geographical region N, and can store satellite images of various periods for each of these geographical regions. In these examples, the satellite image database 104 can store satellite images of each day for the past 10 years for geographical region 1, and satellite images of each day for the past 20 years for geographical region 2.

[0037] In some implementations, the dimensions of the satellite images can correspond to the cameras used on the satellite and the satellite's position location. The satellite can travel around the Earth at a specific distance from the Earth and capture an image of the Earth from that distance. For example, the satellite can travel in a low Earth orbit around the Earth at a distance of 800 kilometers (km) or 497.097 miles from the Earth. In some implementations, the camera associated with the satellite can have a zoom capability.

[0038] In some implementations, the resolution of the satellite camera can be set to a standard resolution to ensure the uniformity of all satellite images. For example, the resolution of the camera can be set to 375 meters horizontally and vertically when capturing a geographical region of the Earth. In other implementations, different satellites can have different resolution capabilities. Therefore, the satellite cameras can adjust their zoom capabilities to ensure that the resolution is uniform across the satellite images from each of the satellites.

[0039] In some implementations, the time database 106 can include one or more databases that store the periods of the satellite images captured by the satellite and stored in the satellite image database 104. The periods can include, for example, defined dates, date ranges, and time ranges. For example, the time database 106 can store a time range from January 1, 2018 to January 1, 2019, or a time range from 12:00 PM on January 1, 2018 to 12:01 PM on January 1, 2019.

[0040] Furthermore, the time database 106 can store an additional specific date range. The more specific date range can include specificity down to the range of hours and minutes. For example, the time database 106 can store a time range from 12:00 PM on January 1, 2018 to 12:30 PM on January 1, 2019.

[0041] In some implementations, the satellite can provide satellite images to the satellite image database 104 along with metadata. The metadata can include location data of the geographical area where the satellite image was captured, data identifying the satellite from which the satellite image was captured, the date and time when the satellite image was captured, and location data indicating where the satellite was located in space when the satellite image was captured. For example, if the satellite captured an image of the geographical area of San Diego, the satellite can associate the following metadata with the image: (1) location data of the geographical area as 32.7515, -117.1364, (2) the date of May 19, 2019 at 12:05 PM PT when the satellite image was captured, (3) data indicating the name and model of the satellite from which the image was captured, e.g., satellite 111 and model 1, (4) location data of the satellite when the image was captured, such as 800 km above the location coordinates of 32.7515, -117.1364. The satellite image database 104 can match the date and location of the wildfire provided by the image server system 102 with the metadata of the satellite images to identify the requested satellite images.

[0042] The image server system 102 can accordingly distribute metadata to each of the databases within the system 100. For example, when a satellite provides a satellite image to the image server system 102, the image server system 102 can provide the satellite image and the metadata to the satellite image database 104 for storage purposes. In addition, the image server system 102 can extract time data from the metadata and provide the time data to the time database 106. The time data can indicate the date and time when the satellite image was captured by the satellite. In addition, the image server system 102 can extract location data of a geographical area from the metadata and provide the location data to the spatial database 108. The image server system 102 can perform this extraction and distribution process for each satellite image obtained from the satellite.

[0043] In some implementations, the spatial database 108 can include one or more databases that store location data of locations identified in satellite images captured by a satellite and stored in the satellite image database 104. The location data can include, for example, latitude and longitude coordinates, addresses, names of landmarks, and dates identifying cities, states, counties, and other data identifying locations on the Earth.

[0044] The spatial database 108 can include one or more bounding boxes indicating the location of an area, such as a geographical area or coordinates, where a wildfire started. The bounding box can include, for example, a polygon indicating the geographical area where the wildfire starts or the area around the geographical area where the fire starts. The bounding box can be applied to the satellite image so that the image server system 102 can determine where to count fire pixels. For example, as further described below, the image server system 102 can count the number of fire pixels within the bounding box applied to the satellite image.

[0045] One or more geographic features and one or more features of wildfires can be included within the polygon. For example, one or more features of wildfires can include one or more areas where no fire is occurring, one or more areas actively on fire, one or more burned areas where a recent fire has occurred, and one or more scar areas resulting from the fire. The spatial database 108 can be populated by the image server system 102 or another external service.

[0046] In response to the image server system 102 obtaining satellite images, the image server system 102 can store data in the time database 106 and the spatial database 108. In some implementations, the image server system 102 can store time data and spatial data from the metadata of the satellite images to ensure that the satellite image database 104 can provide appropriate satellite images when requested. In this case, if the image server system 102 requests a satellite image outside of the data included in the time database 106 and the spatial database 108, the satellite image database 104 can return an error message indicating that the requested data is outside the satellite image range.

[0047] In some implementations, a process external to the image server system 102 can perform the population of the satellite image database 104, the time database 106, and the spatial database 108. In this case, the image server system 102 can perform processes related to determining the time range of wildfires by accessing the time database 106, the spatial database 108, and the satellite image database 104.

[0048] During step (A), the image server system 102 can receive the input date 110 on which the wildfire occurred. As shown in system 100, the input date 110 corresponds to July 5, 2019. In some implementations, an external process can access the time database 106 and provide the input date 110 to the image server system 102. In some implementations, a user interacting with the image server system 102 can request the time range of the wildfire and provide the input date 110 to the image server system 102. Additionally, the input data can be provided, for example, by a fire metadata database. The input date 110 can indicate the day on which the wildfire occurred, and in addition, the satellite image database 104 can provide an indication to the image server system 102 that it includes satellite images of the wildfire in the corresponding geographical location. In other implementations, the image server system 102 can provide a request to the time database 106 to return the date on which the wildfire occurred in a specific geographical location.

[0049] During step (B), the image server system 102 can receive the location 112 where the wildfire occurred based on the input date 110 of the wildfire. As shown in system 100, the location of the wildfire can correspond to location coordinates such as, for example, 33.8121N, -117.91899E. The location 112 can also include other descriptors such as, for example, the name of a landmark, the name of a city, the name of a geographical region, or a specific address.

[0050] In some implementations, the image server system 102 can retrieve a polygon indicating the location where the wildfire first started from the spatial database 108. The image server system 102 can obtain the polygon based on the input date 110 and the location 112. To limit the amount of processing performed by the image server system 102, after retrieving a satellite image from the satellite image database 104, the image server system 102 can apply the obtained polygon to the retrieved satellite image. In this case, the polygon can spatially limit the few pixels searched by the image server system 102 within the satellite image.

[0051] Even if the input date 110 is actually the start date or end date of the wildfire, the input date 110 does not necessarily indicate the start date or end date of the wildfire to the imager server system 102. Rather, the input date 110 can correspond to another date, such as a date between the start date and the end date when the wildfire was active or in progress. As further described below, the image server system 101 can determine where within the time range of the wildfire the input date 110 falls by continuing the process.

[0052] During step (C), the image server system 102 can provide the input date 110 on which the wildfire occurred and the location 112 where the wildfire occurred to the satellite image database 104. The image server system 102 can provide the input date 110 and the location 112 to the satellite image database 104 to obtain satellite images in the location and time range before the input date 110. In some implementations, the image server system 102 can indicate to the satellite image database 104 a period before the input date 110 to obtain satellite images. The period can include, for example, one year before the input date 110, two years before the input date 110, five years before the input date 110, or some other period before the input date 110 that is sufficient to construct a statistical distribution. For example, the image server system 102 may require satellite images for at least one year before the input date 110 to construct a statistical distribution, and as a result, may request satellite images from the satellite image database 104 that are more than two years before the input date 110.

[0053] In some implementations, the satellite image database 104 can index its stored satellite images by location. For example, the image server system 102 can additionally provide the location 112 to the satellite image database 104, and the satellite image database 104 can access satellite images that include the location 112 within its field of view, such as location coordinates or another geographical or location description. The satellite image database 104 can determine the location 112 within the field of view of the corresponding satellite image by analyzing the metadata of the satellite image.

[0054] Next, the satellite image database 104 can filter images that include the location 112 by the time range. For example, the satellite image database 104 can exclude or filter satellite images that have a timestamp and date after the input date 110 and that exist outside the period before the input date 110. For example, the image server system 102 can instruct the satellite image database 104 to provide all satellite images showing the location 112 from two years before the date of July 5, 2019, for example, from July 5, 2017 to July 5, 2019. The image server system 102 can exclude all satellite images showing the location 112 before the date of July 5, 2017 and after the date of July 5, 2019.

[0055] The satellite image database 104 can identify and provide satellite images 114 that meet the criteria of the image server system 102 and return them to the image server system 102. As shown in the system 100, the satellite images 114 can include one or more images or videos of satellite images that include the location 112 and can have timestamps that are within the time range from two years before the input date 110 to the input date 110. In some examples, the satellite images 114 can include satellite images for each day from July 5, 2017 to July 5, 2019, or can include multiple satellite images or videos for each day from July 5, 2017 to July 5, 2019. In some cases, one or more of the days between July 5, 2017 and July 5, 2019 may not include satellite images if the satellite did not capture images around the location 112 on those days.

[0056] In some implementations, each media of the satellite image 114 can include a specified resolution. For example, as described above, each media can include a resolution of 325 meters in the horizontal direction and 325 meters in the vertical direction. With this resolution, the image server system 102 can visually inspect not only the location 112 but also the surrounding area of the location 112. Since wildfires can originate from a specific location and move to another location, by browsing a large area close to the location 112, such as within the bounding box around the location 112, the image server system 102 can improve its determination of the start date and end date of the wildfire. For example, the bounding box or polygon can correspond to an area within the satellite image that indicates the area encompassing the wildfire. The bounding box can include the minimum area covering the wildfire within the satellite image, or an area that includes both the wildfire and the outside of the wildfire.

[0057] In addition, when the location 112 is on the edge of the satellite image 114, the satellite image database 104 can also provide a satellite image adjacent to the location 112 in the satellite image with an edge. In this case, the image server system 102 can ensure that the location 112 shown in the satellite image is always surrounded by an area of the image, for example, by the image resolution, even if the location 112 is on, for example, a vertical or horizontal edge of the satellite image. In some implementations, the image server system 102 can indicate a bounding region or area around the location 112 to the satellite image database 104. Next, when the satellite image database 104 identifies a satellite image that meets the criteria of the image server system 102, the satellite image database 104 can identify additional satellite images to be provided if the initially identified satellite image is not included within the criteria of the bounding region or area.

[0058] In some implementations, the satellite image database 104 can provide the identified satellite images 114 to the image server system 102 via a network. In other implementations, the satellite image database 104 can provide an index of the identified satellite images 114 to the image server system 102 to effect retrieval of the satellite images 114. In some cases, the satellite image database 104 can also provide a link to the identified satellite images 114 for rapid retrieval by the image server system 102. The link can include, for example, a zip file, access to cloud storage, or any other form for downloading the satellite images 114.

[0059] During stage (D), the image server system 102 can generate a statistical distribution based on the identified satellite images 114. In some implementations, the image server system 102 can generate a statistical distribution for comparison with the satellite images to determine the likelihood of wildfires within the satellite images. In particular, the statistical distribution corresponds to a frequency model of satellite noise in a particular geographic area over a period of time. In some examples, the statistical distribution can be modeled using a Poisson distribution, a Gaussian distribution, or a normal distribution.

[0060] In some implementations, the satellite images 114 can depict various landmarks, buildings, roads, and other geographic features. Other geographic features can include, for example, rivers, seas, lakes, hills, and plains. The satellite images 114 can also depict people, vehicles, animals, and other features commonly found in the geographic area. The satellite images 114 can also include noise characteristics such as glare, flashes, and distorted pixels that can make it difficult for the image server system 102 to distinguish wildfires from noise.

[0061] In some implementations, satellite images can indicate various fire areas. These areas can include, for example, one or more areas where no fire is occurring, one or more areas that are actively on fire, one or more burned areas where a fire has recently occurred, and one or more scar areas resulting from the fire. Areas where no fire is occurring can indicate another geographical area where no fire is present. Areas that are actively burning can include, for example, areas indicating active fire, smoke, or residual fire. Burned areas where a fire has recently occurred can indicate geographical areas where the fire once flared up but is no longer active, although those geographical areas are still hot and dangerous. Scar areas can indicate geographical areas that once flared up but are no longer active, and those geographical areas are no longer hot or dangerous.

[0062] The image server system 102 can generate and utilize a statistical distribution to improve the accuracy of detecting ongoing wildfires within satellite images. In particular, the image server system 102 can first start a process of comparing the satellite image with the generated statistical distribution by identifying the number of pixels within the satellite image 114 that appear to indicate a wildfire. Some of the identified pixels may not indicate a wildfire but rather may indicate noisy pixels. To mitigate this problem, the image server system 102 can compare the number of identified pixels within the satellite image 114 that appear to indicate a wildfire with the generated statistical distribution to filter out and remove images with noise characteristics.

[0063] To be able to make such a comparison, the image server system 102 can construct a statistical distribution using historical satellite images obtained from a satellite image database 104 that shows the same locations as the locations 112 that do not show an ongoing wildfire. For example, the image server system 102 must first identify a period prior to the input date 110 within the acquired satellite images 114 that do not show a wildfire. In addition to identifying a date three months prior to the input date 110 to ensure that no wildfire is detected in the corresponding satellite image, the image server system 102 can identify historical weather forecasts and other meteorological databases to check whether there was a fire in a specific geographic area, such as the geographic area identified in the satellite image. By generating a satellite image baseline, the image server system 102 can identify any pixels within the satellite image that are outside the baseline norm and can indicate that the corresponding satellite image appears to show a wildfire. In this case, the image server system 102 first determines the date three months prior to the input date 110. In the example of system 100, the date three months prior to the input date 110 is April 5, 2019.

[0064] The image server system 102 can generally determine the date three months prior to the input date 110 since wildfires generally do not last longer than three months. By identifying the date three months prior to the input date 110, the image server system 102 can safely assume that the same wildfire identified by the input date 110 and location 112 is not active or on fire in the corresponding satellite image, e.g., the satellite image of the date three months prior to the input date 110. In some implementations, if the image server system 102 identifies a wildfire that is still occurring within the satellite image 114 at a date three months prior to the input date 110, the image server system 102 can identify an earlier date. In some cases, the image server system 102 can identify whether one or more other wildfires were active during the period between the input date 110 and the date three months prior to the input date 110. The one or more other wildfires can have different origins and can correspond to wildfires that did not cause the wildfire identified by the input date 110. The image server system 102 can access one or more public wildfire databases to determine whether another wildfire was active during this time window. However, the occurrence of another wildfire that is active within the same geographic area as the wildfire identified by the input date 110 is rare.

[0065] For example, the image server system 102 can set the date back one month from April 5, 2019, for example, to March 5, 2019. If the image server system 102 determines that there are no pixels in the satellite image 114 on March 5, 2019 that appear to indicate a wildfire, the image server system 102 can set March 5, 2019 as the end date of the time range for constructing the statistical distribution. The image server system 102 can repeatedly perform the process of identifying the end date of the time range, for example, going back one day, one month, or one week at a time until the start date without a wildfire is shown in the corresponding satellite image. In this case, the image server system 102 cannot set this determined end date as the actual start date of the wildfire because the wildfire may not actually become active, for example, for one day, one week, or one month after the end date.

[0066] In some implementations, the image server system 102 can determine a date one year before the end date determined for the time range. The date one year before the determined end date of the time range is known as the start date of the time range. The image server system 102 can identify the start date and end date of the time range for identifying satellite images and constructing the statistical distribution. Continuing with the example of system 100, the image server system 102 can determine the start date of the time range to be April 5, 2018, for example, one year before the end date of April 5, 2019.

[0067] However, in order for the image server system 102 to set the start date to April 5, 2018, the image server system 102 can use data from an external database of historical fires to ensure that the satellite image showing location 112 does not indicate an active wildfire between the start date (e.g., April 5, 2018) and the end date (e.g., April 5, 2019). If the image server system 102 identifies data from the external database of historical fires indicating that there was or was an active wildfire in the geographical area from, for example, April 5, 2018 to April 5, 2019, the image server system 102 can adjust the start date or end date accordingly. The manner in which the image server system 102 detects or identifies an ongoing wildfire within the satellite image will be further described below.

[0068] To determine whether the satellite image within the time range indicates an ongoing wildfire, the image server system 102 can identify the number of fire pixels in the satellite image and compare the number of fire pixels to a threshold. For example, the image server system 102 can execute a fire detection algorithm on the satellite image to determine how many pixels contain a fire. The fire detection algorithm can include, for example, an active fire detection algorithm. If the number of fire pixels in the satellite image is less than the threshold, the image server system 102 can indicate that a particular satellite image does not contain a fire.

[0069] For example, the image server system 102 can select a subset of satellite images from the satellite image 114, including the extreme values, for the period from April 5, 2018 to April 5, 2019. The image server system 102 can process each image or video from each day within that time range and search for pixels that appear to indicate a wildfire. If the image server system 102 detects pixels that appear to indicate a wildfire on April 8, 2018, for example, where the number of pixels is greater than a threshold and not detected on other days, the image server system 102 can adjust the time range to April 9, 2018 to April 5, 2019. Alternatively, if the image server system 102 detects pixels that appear to indicate a wildfire on April 1, 2019, for example, where the number of pixels is greater than a threshold, the image server system 102 can adjust the time range to April 5, 2018 to March 31, 2019.

[0070] In some cases, if the image server system 102 detects pixels that appear to indicate a wildfire at the center of the time range, such as on December 1, 2018 or November 1, 2018, for example, where the number of pixels is greater than a threshold, the image server system 102 can exclude those days from the time range and adjust the time range into multiple consecutive sub-time ranges. For example, the consecutive sub-time ranges can include from April 5, 2018 to October 31, 2018, from November 2, 2018 to November 30, 2018, and from December 2, 2018 to April 5, 2019. Thus, the image server system 102 can create a single continuous time range or multiple consecutive sub-time ranges to construct the satellite image distribution.

[0071] In some implementations, the image server system 102 can determine a date that is 9 months before a date that is 3 months before the input date 110. For example, if the image server system 102 determines that a satellite image with a date of April 5, 2019 does not appear to show a wildfire, the image server system 102 can identify a date that is 9 months before the date of April 5, 2019 for the start of the time range. The end date of the time range is April 5, 2019. The date 9 months before April 5, 2019 corresponds to July 5, 2018. Thus, the image server system 102 can construct a statistical distribution based on the time range from July 5, 2018 to April 5, 2019.

[0072] If the image server system 102 is based on a shorter 9-month time range for the statistical distribution, for example, from July 5, 2018 to April 5, 2019, the image server system 102 can generate the statistical distribution more quickly and save processing speed / power. However, if the image server system 102 is based on a longer 1-year time range for the statistical distribution, for example, from April 5, 2018 to April 5, 2019, the image server system 102 can generate a more accurate and representative statistical distribution of location 112. In some examples, typically, wildfires can occur in a specific region, such as the California region, during the typical 3-month fire season that starts around August and September. For fires that occur during this fire season, a 9-month window can be selected instead of a 1-year window to reduce the likelihood of selecting satellite images that incidentally include wildfires from the previous fire season in the baseline distribution. In some implementations, the image server system 102 can remove the fire season corresponding to the time range from the satellite images to reduce the likelihood of fires being incidentally included within the time range or baseline distribution.

[0073] In response to identifying satellite images within the time range identified from satellite image 114, image server system 102 can determine the number of pixels that appear to indicate wildfires on each day within the identified satellite images. For example, image server system 102 can analyze the satellite images on each day during the identified time range from April 5, 2018 to April 5, 2019, and can determine the number of fire pixels on each day. In some implementations, image server system 102 can apply polygons retrieved from spatial database 108 to the identified satellite images. By cropping the identified satellite images with the polygons, image server system 102 can reduce the amount of pixels searched across the identified satellite images. In this case, image server system 102 can search across the pixels within the identified satellite images within the retrieved polygons.

[0074] For example, image server system 102 can count 10 fire pixels on April 5, 2018, count 11 fire pixels on April 6, and continue to count satellite images on each day until April 5, 2019. The same process is similar when analyzing satellite images within a one-year time range or a time range with multiple consecutive sub-time ranges.

[0075] In some implementations, image server system 102 can normalize the number of fire pixels detected on each day. For example, image server system 102 can analyze 1 satellite image on April 5, 2018, analyze 50 satellite images on April 6, 2018, and analyze 10 satellite images on April 7, 2018. Image server system 102 can normalize the detections by dividing by the average number of fire pixels detected on each day. The reason for normalization is to ensure that the generated statistical distribution produces a smooth curve. If the values are not normalized, the curve of the generated distribution can include jagged edges and can distort probability predictions.

[0076] In some implementations, after determining the number of fire pixels for each day within the satellite image or within the polygon of the satellite image for the identified time range, the image server system 102 can generate a statistical distribution. For example, the image server system 102 can generate a frequency histogram of the number of identified pixels within the satellite image that appears to indicate an ongoing wildfire. The frequency histogram can be represented as a graph with the number of days on the X-axis and the number of fire pixels on the Y-axis.

[0077] Next, the image server system 102 can determine the mean of the frequency histogram and apply other data descriptors such as the mean or standard deviation to the statistical distribution. For example, the image server system 102 can fit the mean of the frequency histogram to a Poisson distribution or another statistical distribution. In a Poisson distribution, the mean is equivalent to the variance. In the case of system 100, the average number of identified pixels that indicate wildfires over a given time interval, such as one year, is equivalent to the variance of the Poisson distribution.

[0078] In some implementations, if a significant number of wildfire events are inadvertently included in the baseline distribution, the baseline distribution may no longer have equivalent mean and variance. In other words, the baseline distribution may no longer follow a Poisson distribution. In this case, the image server system 102 can perform a test to determine whether the baseline distribution, e.g., the mean and variance of the statistical distribution, are equivalent. The test can be performed, for example, by analyzing the mean of the samples in the statistical distribution and analyzing the variance of the samples. If the image server system 102 detects that the mean and variance of the statistical distribution are not equivalent, the image server system 102 can adjust the time range and the corresponding satellite images and construct a new statistical distribution based on the satellite images from the adjusted time range. The image server system 102 can repeat this process until a statistical distribution with equivalent mean and variance is constructed. Once the statistical distribution is constructed, only one parameter, such as the average number of pixels that appear to indicate a wildfire, is required to determine the probability of the event. The following equation shows the probability distribution function of a Poisson random variable.

[0079]

Number

[0080] In the above Equation 1 showing the Poisson distribution, the value λ corresponds to the average number of pixels that appear to indicate a wildfire from the baseline. The value k corresponds to the number of times a random variable or event occurs, e.g., the number of pixels that appear to indicate a wildfire in the input image. The resulting value, f(k;λ), corresponds to the probability representing the Poisson probability distribution function. In some implementations, when the value λ is determined, the image server system 102 can return the Poisson distribution 116.

[0081] The Poisson distribution 116 can provide a value that results during the comparison with the input image, and the resulting value indicates the likelihood that an event will occur within a given period. In particular, the probability density function (PDF) of the Poisson distribution 116 can return the probability that a particular day with k counted pixels occurred naturally from the noise distribution. Therefore, the lower the value output by the PDF, the higher the likelihood that an external force, such as a wildfire, contributed to the count of the k value. Alternatively, the higher the value output by the PDF, the lower the likelihood that an external force contributed to the count of the k value, indicating that the image is more closely similar to an image from the baseline distribution. For example, when the probability corresponds to a low value such as 0.01, the image server system 102 can determine that the image is likely to indicate a wildfire. Alternatively, when the probability corresponds to a high value such as 0.90, the image server system 102 can determine that the image is unlikely to indicate an ongoing wildfire.

[0082] During step (E), the image server system 102 can determine the start date of the wildfire based on the generated statistical distribution and the satellite image 114. For example, as shown in system 100, the image server system 102 can generate the statistical distribution 116 during step (D). Next, the image server system 102 compares each of the satellite images 114 starting from the input date 110 of July 5, 2019 with the generated statistical distribution 116.

[0083] First, the image server system 102 determines the number of pixels in the satellite image of July 5, 2019 that appear to indicate a wildfire from the satellite image 114. In some implementations, the image server system 102 can use a fire detection algorithm to determine whether a pixel indicates a wildfire. In other implementations, the image server system 102 can analyze the brightness of the pixels to determine whether a pixel indicates a wildfire. For example, the image server system 102 can analyze the brightness of each pixel and compare the brightness of the pixel with a threshold value to determine the number of pixels in the satellite image on July 5, 2019 that appear to indicate a wildfire. For example, the image server system 102 can determine the brightness of a pixel by averaging the red, blue, and green (RGB) values of the pixel. In some implementations, the image server system 102 can analyze wavelengths outside the RGB values to determine which pixels are in a fire. For example, an infrared wavelength can be mentioned as a wavelength outside the RGB. The lower the average, the lower the brightness of the pixel, and vice versa. In another example, the image server system 102 can determine the brightness of a pixel by calculating a relative brightness value using the following formula. Y = 0.2126*R + 0.7152*G + 0.0722*B (2)

[0084] The above formula 2 indicates calculating the relative luminance value of a pixel based on the RGB values of the pixel. For example, when the red value of a pixel is 100, the green value is 100, and the blue value is 100, the relative luminance value is 100. The larger the relative luminance value, the greater the brightness of the pixel. The brightness of a pixel does not indicate whether the pixel indicates a wildfire or noise, but the brightness of the pixel may be an indication that the pixel appears to be in a fire. In some implementations, the image server system 102 can also analyze the intensity of the pixel to determine whether there is a wildfire in the pixel. In other implementations, the image server system 102 can determine whether the corresponding pixel indicates a wildfire depending on an external source. For example, the image server system 102 can utilize the VIIRS (Visible Infrared Imaging Radiometer Suite) Active Fire Product developed by NASA to combine the infrared band from a satellite image with the RGB bands of the pixel to determine whether the pixel was in a fire. Usually, each satellite includes a unique detection algorithm optimized for the specifications of the corresponding device.

[0085] In some implementations, the image server system 102 can apply the polygon obtained from the spatial database 108 to the satellite image of a specific day. The image server system 102 can analyze the brightness or intensity of each pixel and compare the brightness of the pixel with a threshold value to determine the number of pixels that appear to indicate a wildfire within the polygon of the satellite image on July 5, 2019. By incorporating the polygon onto the satellite image, the image server system 102 can reduce the complexity of processing and shorten the processing time because a smaller amount of pixels in the satellite image are searched.

[0086] The image server system 102 can calculate the brightness of each pixel within the satellite image of July 5, 2019, or within the polygon applied to the satellite image of July 5, 2019. Next, for each pixel, the image server system 102 can compare the brightness of each pixel with a threshold value. For example, the image server system 102 can specify a threshold value of 50 or other brightness values. If a particular pixel in the satellite image is greater than the threshold value, the image server system 102 can consider that pixel to be included in the count. The image server system 102 repeats this process for each pixel in the satellite image.

[0087] In some implementations, the image server system 102 can identify pixels indicating wildfires within the satellite image. Depending on the situation, the pixels that can indicate wildfires can correspond to areas within the polygon, for example, areas that are actively on fire and potential combustion areas where a fire has recently occurred. If the combustion area where a fire has recently occurred includes one or more remaining fires from the fire, the image server system 102 can detect and identify the pixels associated with those remaining fires within the satellite image as pixels that are on fire. However, pixels associated with areas where no fire has occurred and scar areas resulting from the fire are not detected by the image server system 102 as indicating a fire.

[0088] Next, the image server system 102 can input the number of counted pixels in the satellite image into the value of k in Equation 1 of the Poisson distribution 116. For example, the image server system 102 can fit a frequency histogram to the Poisson distribution and obtain the following equation.

[0089]

Number

[0090] As shown in Equation 3, the number 5 instead of the value λ corresponds to the average number of pixels that appear to indicate wildfires from the baseline distribution for each day. Further, the value λ can describe the spread of the Poisson distribution curve. Equation 3 represents the probability density function or the continuous probability density function of the Poisson distribution. The value k corresponds to the number of pixels found in the satellite image of July 5, 2019 that appear to indicate wildfires. For example, if the pixel count of a particular image corresponds to a value of 6, Equation 3 should yield the following values.

[0091]

Number

[0092] As shown in Equation 4, the image server system 102 calculated a 14.62% probability that an event of six fire pixels is likely to occur in the baseline distribution. Further, the calculated probability indicates the number of events (e.g., fire pixels) that occurred in the satellite image on one day (e.g., July 5, 2019) relative to the known average proportion of fire pixels that occurred over a one-year period (e.g., from April 5, 2018 to April 5, 2019) as determined from the baseline distribution.

[0093] In some implementations, the calculated probability can correspond to a metric that is a proxy for the probability that the satellite image is not in a fire. Given this proxy, the image server system 102 can determine whether the satellite image indicates a wildfire depending on which side of the threshold the likelihood falls. If the likelihood is greater, the likelihood can indicate that the satellite image indicates a wildfire. Alternatively, if the likelihood is smaller, the likelihood can indicate that the satellite image does not indicate a wildfire.

[0094] Next, the image server system 102 can compare the output probability with a threshold value to determine whether the satellite image of July 5, 2019 has the same number of fire pixels as the baseline distribution. For example, the image server system 102 may set the threshold value to 5% or 0.05. If the image server system 102 determines that the output probability is less than the threshold value, the image server system 102 can determine that the satellite image is likely to indicate a fire. Alternatively, if the image server system 102 determines that the output probability is greater than the threshold value, the image server system 102 can determine that the satellite image does not contain a fire.

[0095] If the image server system 102 determines that the output probability is less than the threshold value, the image server system 102 repeats the process of comparing the average number of pixels that appear to indicate a wildfire with the previous day. For example, the image server system 102 can obtain the satellite image of July 4, 2019 from the satellite image 114. Next, the image server system 102 can determine the number of pixels in the satellite image of July 4, 2019 that appear to indicate a wildfire, for example, using a fire detection algorithm. The image server system 102 can determine a probability from a statistical distribution based on the count of fire pixels on that day. Next, the image server system 102 can compare the probability from the statistical distribution with a threshold value to determine whether the satellite image includes the likelihood of a fire.

[0096] The image server system 102 repeats this process until the probability from the statistical distribution is greater than the threshold. In some implementations, if the image server system 102 determines that the probability that a satellite image for a particular day indicates a wildfire is greater than the threshold, the image server system 102 can consider that there is no fire in this satellite image. In this case, the image server system 102 can identify the first occurrence of a satellite image that generates a probability based on the statistical distribution and the number of pixels greater than the threshold. In some implementations, the image server system 102 can consider that date to be the date on which the wildfire occurred. As shown in system 100, this start date 118 or the date on which the wildfire occurred corresponds to June 1, 2019, because the satellite images on June 2, 2019, July 4, 2019, and July 5, 2019, indicate fires, while the satellite images do not indicate an ongoing wildfire.

[0097] In other implementations, if the statistical distribution outputs a probability greater than the threshold for the identified date, the image server system 102 can perform an additional process. In particular, the image server system 102 can perform a verification that the identified date on which the wildfire occurred is actually accurate and not determined from an error. For example, the image server system 102 can determine that the identified date on which the wildfire occurred was not determined by noise such as clouds or smoke found in the satellite image. To verify, the image server system 102 can calculate the probability using the statistical distribution 116 for each day one week before the identified start date.

[0098] For example, if the image server system 102 determines that the identified date is June 1, 2019, the image server system 102 can perform an additional verification process of calculating probabilities using the statistical distribution 116 for each day before June 1, 2019, for example, each day going back to May 25, 2019. The image server system 102 can, for example, obtain satellite images for each day from May 25, 2019, to May 31, 2019, and count the number of fire pixels for each day from May 25, 2019, to May 31, 2019. Next, for the pixel count from each day, the image server system 102 can calculate the corresponding probability using the statistical distribution 116 from each day. If each corresponding probability is greater than a threshold value, for example, if it shows a probability high enough to be classified as a day without a fire, the image server system 102 can consider the day of June 1, 2019, as the true date when the wildfire occurred. Otherwise, if one of the days within the previous week's period shows a probability lower than the threshold value, for example, if one of these days shows a wildfire, the image server system 102 can continue to iterate in the reverse direction to find the actual start date of the wildfire and then the "fire-free" days for the entire previous week. The same process also applies to finding the end date of the wildfire.

[0099] In some implementations, the image server system 102 may need to adjust the identified start date or end date. For example, the image server system 102 may determine that the satellite cannot identify a wildfire until two days after the start date. To solve this problem, the image server system 102 can subtract two days from the identified start date to ensure accurate time range detection. For example, if the image server system 102 identifies June 1, 2019, as the start date, the image server system 102 can move the date back two days, for example, to May 30, 2019, to account for inconsistent detections with the satellite. Other days such as three days, four days, or five days may also be possible.

[0100] In some implementations, the image server system 102 can adjust the identified start date based on the rate of change of the intensity of the fire. For example, if the image server system 102 notices that the intensity has changed by 60 between one day and the next for a satellite image, the image server system 102 can roll back the date by three days, for example, to May 29, 2019. If the image server system 102 notices that the intensity has changed by 40 between one day and the next for a satellite image, the image server system 102 can roll back the date by four days, for example, to May 28, 2019. Typically, a rapidly expanding fire requires less adjustment than a slowly spreading fire. This process is the same for adjusting the identified end date.

[0101] During step (F), the image server system 102 can generate a second statistical distribution using the start date 118 of the wildfire. As shown from system 100, the start date 118 of the wildfire occurred one month and four days before the provided input date 110. The image server system 102 can determine the end date 124 of the wildfire based on the second generated statistical distribution.

[0102] First, the image server system 102 can provide the start date 118 and the location 112 to the satellite image database 104 to obtain satellite images for generating the second statistical distribution. Step (F) is similar to step (C) in that the date and location are provided to the satellite image database 104 and the satellite image database 104 returns a satellite image indicating the location. However, in step (F), the image server system 102 can also instruct the satellite image database 104 to provide satellite images from both before and after the start date 118. The image server system 102 can generate the second statistical distribution based on the satellite images before the start date 118 and can determine the end date 124 of the wildfire based on a comparison of the satellite images after the start date 118 and the second statistical distribution.

[0103] For example, the image server system 102 can indicate to the satellite image database 104 a period around the start date 118 in order to acquire satellite images. The period around the start date 118 can be determined based on the amount of time required to construct the second statistical distribution, for example, the period before the start date 118, and the amount of time required to identify the end date, for example, the period after the start date 118. For example, the image server system 102 can identify a period of one year and three months, which is one year before the start date 118 to construct the second statistical distribution and three months after the start date 118 of the satellite image to determine the end date 124. In other examples, the image server system 102 can request a large number of satellite images, such as a two-year, five-year, or longer period centered around the start date 118.

[0104] During step (G), the satellite image database 104 can provide the identified satellite images 120a and 120b to the image server system 102 via the network. The satellite image database 104 can provide the satellite images 120a and 120b via the network in the form of an email, a zip file, or another format. In some examples, the satellite image database 104 can send an index for retrieving the satellite images 120a and 120b to the image server system 102.

[0105] For example, the satellite image 120a can correspond to a satellite image acquired before the start date 118. The satellite image 120b can correspond to a satellite image acquired after the start date 118. The image server system 102 can generate a second statistical distribution based on the satellite image 120a. In addition, the image server system 102 can determine the end date 124 based on the generated second statistical distribution and the satellite image 120b.

[0106] During step (H), the image server system 102 can generate a second statistical distribution based on the identified satellite image 120a and the determined start date 118. Step (H) is similar to step (D). However, during step (H), since the start date 118 is known, the image server system 102 does not need to determine the date three months before the input date. In this case, the image server system 102 can identify the time region before the start date 118.

[0107] In some implementations, the image server system 102 can return an error, the identified time range, or both. The image server system 102 can return an error, for example, when an end date is requested for an ongoing wildfire, when satellite images are unavailable or of low quality in the time and geographical location of historical fires, when satellite data is unavailable or of low quality in the time range used to construct the noise distribution, or in other cases. The error can indicate, for example, "insufficient satellite images", "ongoing wildfire", or "low-quality satellite images". In other examples, when the baseline distribution is too close to the current date, e.g., within one day, several days, or one week, the image server system 102 can indicate that it can accordingly shift the baseline distribution to an earlier period.

[0108] For example, the image server system 102 can generate a time range one year before the start date 118. In this example, the image server system 102 can generate a time range from June 1, 2018 to June 1, 2019 to obtain satellite images and construct a second statistical distribution. As done in step (C), the image server system 102 can ensure that there are no active wildfires in the satellite images during this time range. If the image server system 102 detects an ongoing wildfire in this satellite image, for example, or within the polygon of the satellite image, the image server system 102 can adjust the time range accordingly to avoid the satellite image indicating an active wildfire.

[0109] In some implementations, once the time range is identified, the image server system 102 can generate a second statistical distribution 122. In particular, the image server system 102 can generate the second statistical distribution 122 based on a subset of the satellite images 120a that match the identified time range, for example, from June 1, 2018 to June 1, 2019. The second statistical distribution 122 can also be in the form of, for example, a Poisson distribution, a normal distribution, or a Gaussian distribution in some cases. In some cases, the value λ for the second statistical distribution 122 may be different from the value λ for the first statistical distribution 116.

[0110] During step (I), the image server system 102 can determine the end date 124 of the wildfire based on the generated second statistical distribution 122 and the satellite image 120b. The function of step (I) is similar to the function of step (E). However, the image server system 102 compares each of the satellite images from the satellite image 120b starting from the start date of June 1, 2019 with the generated second statistical distribution 122.

[0111] For example, the image server system 102 can acquire the satellite image of June 1, 2019 from the satellite image 120a. Next, the image server system 102 can determine the number of pixels in the satellite image of June 1, 2019 that appear to indicate a wildfire by counting each of the pixels that appear to indicate a wildfire. For example, the image server system 102 can identify the number of pixels within the polygon region of the satellite image of June 1, 2019 that appear to indicate a wildfire. The image server system 102 can determine a probability from the second statistical distribution 122 based on the count of fire pixels in the image. Next, the image server system 102 can compare the probability from the statistical distribution with a threshold value to determine whether the satellite image includes the likelihood of a fire.

[0112] If the image server system 102 determines that the probability that a satellite image on a specific day, e.g., June 2, 2019, indicates a wildfire is less than the threshold, the image server system 102 can consider this satellite image as seemingly indicating a fire. In this case, the image server system 102 identifies the satellite image for the next day in the future, e.g., the satellite image for June 3, 2019, from the satellite image 120b. The image server system 102 can traverse forward in time to find the end date of the wildfire. In particular, the image server system 102 repeats this process until the probability from the statistical distribution becomes greater than the threshold and the probability for some consecutive number of days immediately after the potential end date also becomes greater than the threshold. This number of days may be, for example, 6, 7, 8, or some other number. This process for verifying that the potential end date of the wildfire is actually correct is similar to the verification of the correctness of the dates of the previous potential states of the wildfire. However, instead of using the statistical distribution 116 for each day one week before the potential start date to calculate the probability, in this process, the image server system 102 uses the statistical distribution 122 for each day one week after the potential end date to calculate the probability in order to identify days with "no fire". If the next one-week period results in one or more days indicating a wildfire, the image server system 102 can continue to iterate in the forward direction to identify the actual end date of the wildfire.

[0113] In some implementations, if the image server system 102 determines that the probability that a satellite image on a specific day indicates a wildfire is greater than the threshold, the image server system 102 can consider that there is no fire in this satellite image. Then, the image server system 102 can repeat the process of using the statistical distribution to calculate the probability for a consecutive number of days, e.g., one week, after the potential day to identify whether the potential day corresponds to the actual end date. If the image server system 102 determines that the probability generated for each day after the potential date is greater than the threshold, the image server system 102 can consider that date as the date when the wildfire ended.

[0114] In some implementations, the image server system 102 can determine the end date 124 of the wildfire by analyzing the pixels within one or more burned areas where a fire has recently occurred and one or more scar areas resulting from the fire. The image server system 102 can determine that these corresponding pixels within the polygon of the satellite image correspond to the burned area or the scar area. Additionally, when identifying the end date 124, the image server system 102 can expand the polygon area overlaid on the satellite image. By expanding, the image server system 102 can identify the pixels within the maximum perimeter of the polygon to ensure that the wildfire has not spread to other areas within the satellite image.

[0115] In some implementations, the image server system 102 can include multiple surrounding polygons within the satellite image over the lifespan of the wildfire. In this case, when constructing the statistical distribution 116, the image server system 102 can crop the polygon closest to the satellite data after the input date 110. Additionally, when constructing the statistical distribution 122, the image server system 102 can crop the oldest polygon. The image server system 102 can select the polygon closest to the statistical distribution 116 and the oldest polygon for the statistical distribution 122 to reduce the noise when determining the start date. When the image server system 102 views the satellite image within an area known not to have burned as a result of the wildfire during a specific day, the image server system 102 counts only the noisy pixels without the wildfire. Therefore, if the image server system 102 only counts the fire pixels, the accuracy of the start date prediction decreases.

[0116] As shown in system 100, the satellite image on June 1, 2019 appears to show a wildfire, the satellite image on June 2, 2019 appears to show a wildfire, the satellite image on August 4, 2019 appears to show a wildfire but is smaller, and the satellite image on August 5, 2019 does not appear to show a wildfire. Assuming that the image server system 102 does not detect a wildfire on days after August 5, 2019, for example, from August 6, 2019 to August 13, 2019, the image server system 102 can define the end date 124 or the date when the wildfire ended as August 5, 2019.

[0117] During step (J), the image server system 102 can provide the output time range of the wildfire to one or more pipelines. As shown in system 100, based on the first statistical distribution 116, the second statistical distribution 122, and the corresponding satellite images, the image server system 102 determined that the time range of the wildfire is from June 1, 2019 to August 5, 2019. Further, the image server system 102 can determine that this time range is accurate because the length of the time range is less than three months, for example, less than the maximum amount of time the fire persists, and the input date 110 falls within the time range.

[0118] In some implementations, the image server system 102 can provide a time range to one or more internal or external pipelines. The internal pipeline can be, for example, different machine learning models as training data. The different machine learning models can implement applications such as monitoring wildfires and their spread. Other internal pipelines can include, for example, different graphical representations of wildfires or other user interfaces for indicating the spread of wildfires. The external pipeline can be, for example, other external systems that perform wildfire detection, dispatching responders to extinguish wildfires, and remotely monitoring crises such as wildfires or other climate disasters. The image server system 102 can also provide the time range of the wildfire to other systems. For example, as shown in system 100, the image server system 102 can output the time range to monitor 126 for review.

[0119] The image server system 102 can obtain satellite images having known start and end dates from the satellite image database 104 to verify the authenticity of the processes of system 100. For example, the image server system 102 can obtain a plurality of satellite images corresponding to the date in the middle of the identified time range. The image server system 102 then provides each satellite image from the plurality of satellite images to the processes shown in system 100 to determine whether the image server system 102 can identify the same time range, for example, the same start and end dates. If the image server system 102 can identify the same time range for each satellite image, the processes shown in system 100 appear to be functioning properly.

[0120] FIG. 2A is a block diagram showing an example of a system 200 for receiving satellite images and generating a time range of wildfires from the satellite images. System 200 includes components similar to those of system 100 and performs similar functions. For example, system 200 includes a satellite 202, an image server system 204, a time database 214, a spatial database 216, and a satellite image database 218. System 200 also includes a network 205 that can include any of a satellite network, a local connection, or another connection over the Internet.

[0121] During step (A), the image server system 204 can send a request 203 to the satellite 202 via the network 205. The request 203 can instruct the satellite 202 to capture one or more satellite images of a geographic area on the Earth. The request 203 can include location coordinates of the area, such as latitude and longitude coordinates, to capture one or more images as the satellite 202 travels around the Earth.

[0122] During step (B), the satellite 202 can capture one or more satellite images of the geographic area provided by the request 203. The satellite 202 can include one or more satellite cameras for capturing satellite images. For example, as shown in system 200, the geographic area can include one or more mountains, hills, fires, and smoke. Other geographic areas can include more, fewer, or different geographic features than those shown in system 200. The satellite 202 can capture a satellite image 206 of the requested geographic area as the satellite 202 travels around the Earth.

[0123] For example, satellite 202 can navigate on a daily basis across a requested geographic area and thus can provide satellite images of the requested geographic area on a daily basis. In some implementations, satellite 202 may capture a geographic area with multiple images, multiple videos, or both per day. In this case, image server system 102 may be able to view multiple satellite images and videos on one day and a different set of multiple satellite images and videos on the next day, etc. By providing a set of media, image server system 204 can improve the accuracy of wildfire detection over that time range.

[0124] In some implementations, one or more geographic areas captured by a satellite camera may include one or more locations associated with a wildfire. For example, one or more locations associated with a wildfire can include one or more areas where no fire is occurring, one or more areas that are actively on fire, one or more burned areas where a fire has recently occurred, and one or more scar areas resulting from the fire. As shown in system 201, one or more locations associated with a wildfire within a geographic area can include one or more areas 211 where no fire is occurring, one or more areas 210 that are actively on fire, one or more burned areas 208 where a fire has recently occurred, and one or more scar areas 212 resulting from the fire.

[0125] Each of areas 208, 210, 211, and 212 can be adjacent to each other within the geographic area. When satellite 202 captures one or more images of a geographic area based on the location in request 203, the satellite image can include one or more of these areas. For example, satellite 202 can capture an image that includes the location from request 203, and the image can include area 210 that is actively on fire, burned area 208 where a fire has recently occurred, and one or more scar areas 212 resulting from the fire. Other satellite images can include other areas, such as each of the areas shown in system 100.

[0126] Next, satellite 202 can transmit the captured media 206 to the image server system 204 via network 205. In some implementations, satellite 202 can transmit the captured media 206 directly to the satellite image database 218, bypassing the image server system 204 directly. In this case, at a later time, the image server system 204 can obtain data identifying the captured media 206 and determine the time range of the wildfire indicated by the captured media. For example, the data identifying the captured media 206 can include, for example, location data and the specific time when the wildfire indicated by the captured media 206 was active.

[0127] During step (C), the image server system 204 obtains the input date 220 of the wildfire and the corresponding location 222 of the wildfire. Step (C) of system 200 is similar to steps (A), (B), and (C) of system 100. In particular, as shown in system 200, the image server system 204 obtains an input date 220 of July 5, 2019 and a location 222 of 33.8121N, -117.91899E for the corresponding wildfire. In some implementations, the image server system 204 can obtain a polygon to apply to the satellite image to reduce the amount of pixels to be searched. The polygon can be obtained from the spatial database 216. The polygon can spatially limit the number of pixels searched by the image server system 102 for fire pixels. For example, the image server system 204 can apply polygon 226 to the obtained satellite image 224. The corresponding wildfire can correspond to the captured wildfire within the satellite image 206, or instead, a previously captured satellite image stored in the satellite image database 218 can be referenced.

[0128] The image server system 204 can provide the date 220 on which the wildfire occurred and the location 222 where the wildfire occurred to the satellite image database 218. In addition, the image server system 204 can indicate the period of satellite image retrieval. For example, the image server system 204 can instruct the satellite image database 218 to provide the date of July 5, 2019 indicating the location 222 and all satellite images starting from 2 years ago. The image server system 204 can also request the satellite image database 218 for satellite images having different periods such as, for example, one year, three years, five years, or more. In response, the satellite image database 218 can return the satellite image 224 to the image server system 204 based on the criteria specified by the image server system 204. Next, the image server system 204 can apply the polygon 226 to the acquired satellite image 224 to spatially limit the area that the image server system 204 searches for fire pixels.

[0129] During step (D), the image server system 204 can generate a first statistical distribution based on the acquired satellite image 224. Step (D) of system 200 is the same as step (D) of system 100.

[0130] In particular, the image server system 204 can determine a time range for identifying a subset of the satellite image from the satellite image 224. The image server system 204 identifies a date 3 months before the input date 220, for example, April 5, 2019. Next, the image server system 204 determines either a one-year time range (e.g., April 5, 2018 - April 5, 2019) or a nine-month time range (e.g., July 5, 2019 - April 5, 2019) to construct a satellite image baseline.

[0131] In response to the identification of the time range, the image server system 204 can identify a subset of satellite images from the satellite image 224 using the identified time range. For example, the image server system 204 can identify from the satellite image 224 satellite images from April 5, 2018 to April 5, 2019, and ensure that the identified satellite images do not show wildfire pixels, for example, do not show satellite images within a threshold. Next, the image server system 204 can determine the average number of fire pixels found in the identified satellite images within the time range, and generate a first statistical distribution by fitting the average number of fire pixels to a statistical distribution. The statistical distribution may be, for example, a Poisson distribution where the mean is equivalent to the variance.

[0132] During step (E), the image server system 204 can determine the number of pixels in the satellite image that appear to indicate an active wildfire from the satellite image 224. Step (E) of system 200 is similar to step (E) of system 100. In particular, the image server system 204 can use, for example, a fire detection algorithm or brightness threshold detection to count the detected fire pixels, and determine the number of pixels within a polygon in the satellite image that appears to indicate a wildfire on a specific day, for example, July 5, 2019.

[0133] During step (F), the image server system 204 can compare the number of detected fire pixels with the generated statistical distribution. Step (F) of system 200 is similar to step (E) of system 100. For example, if the generated statistical distribution is a Poisson distribution, the image server system 204 can determine the probability by providing the number of fire pixels detected for a specific image as a value in the Poisson distribution. The Poisson distribution can return a probability indicating the likelihood of an event occurring, for example, the likelihood that a specific image on July 5, 2019 shows a wildfire. The image server system 204 can compare the probability with a threshold to determine whether the satellite image for a specific day has a similar number of fire pixels.

[0134] When the image server system 204 determines that the probability output by the generated statistical distribution is less than the threshold value, during step (G), the image server system 204 acquires the satellite image of the previous day. Step (G) of system 200 is the same as step (E) of system 100. For example, the image server system 204 acquires the satellite image of July 4, 2019, and repeats the processes of steps (E) and (F) of system 200. The image server system 204 repeats the processes of steps (E), (F), and (G) until the start date of the wildfire is identified. Therefore, the image server system 204 continuously goes back one day at a time until the corresponding satellite image indicating location 222 no longer shows an active or ongoing wildfire, for example, until the probability output by the generated statistical distribution is greater than the threshold value.

[0135] Alternatively, when the image server system 204 determines that the probability output by the generated statistical distribution is greater than the threshold value, during step (H), the image server system 204 indicates that the start date 228 of the wildfire has been identified, assuming that the image server system 204 did not detect a wildfire for a predetermined number of days before the potential start date 228. As shown in system 200, the start date 228 of the wildfire corresponds to June 1, 2019. Step (H) of system 200 is the same as steps (F) and (G) of system 100.

[0136] For example, during step (H), the image server system 204 can provide the identified start date 220 and location 222 to the satellite image database 218 to acquire satellite images for generating a second statistical distribution. Here, the image server system 204 can also instruct the satellite image database 218 to provide satellite images from both before and after the start date 228. For example, the image server system 204 can specify a specific time frame (e.g., one year and three months) around the start date 228 or request a large time frame (e.g., two years, five years, or more) around the start date 228.

[0137] In some implementations, the satellite image database 218 can return the acquired satellite image 232 based on the criteria identified by the image server system 204. In particular, the satellite image 232 can include, for example, satellite images before the identified start date 228 for constructing a second statistical distribution and, for example, satellite images after the identified start date 228 for identifying the end date of a wildfire.

[0138]

[0138] During stage (I), the image server system 204 can generate a second statistical distribution based on the satellite image 232 before the identified start date 228 and the identified start date 228. Stage (I) of system 200 is similar to stage (H) of system 100. At this stage, the image server system 204 can identify the time range before the start date 228 to construct the second statistical distribution. The image server system 204 can extract a subset of satellite images from the satellite image 232 based on the identified time range. Next, the image server system 204 can fit the subset of satellite images to a statistical distribution such as a Poisson distribution, a normal distribution, or a Gaussian distribution.

[0139]

[0139] During stage (J), the image server system 204 can determine the number of pixels in the satellite image that appear to indicate a wildfire from the satellite image 232 after the start date 228. Stage (J) of system 200 is similar to stage (I) of system 100. In this case, the image server system 204 can count the number of pixels in the satellite image that appear to indicate a wildfire for a specific day, such as June 1, 2019, by determining the brightness of each pixel or by using a fire detection algorithm.

[0140] During step (K), the image server system 204 can compare the count of fire pixels for a specific image on a specific day with the generated second statistical distribution. Step (K) of system 200 is similar to step (F) of system 200. The generated second statistical distribution can generate the probability indicating the likelihood of an event occurring, for example, the likelihood that a specific image on June 1, 2019 indicates a wildfire. The image server system 204 can compare the probability with a threshold to determine whether the satellite image of a specific day has a similar number of fire pixels.

[0141] If the image server system 204 determines that the probability output by the generated second statistical distribution is less than the threshold, during step (L), the image server system 204 acquires the satellite image of the next day. Step (L) of system 200 is similar to step (I) of system 100. For example, the image server system 204 acquires the satellite image of June 2, 2019 and repeats the processes of steps (J) and (K) of system 200. The image server system 204 repeats the processes of steps (J), (K), and (L), advances one day at a time until the end date of the wildfire is identified and it is assumed that the image server system 204 does not detect a wildfire for a predetermined number of days after the potential end date.

[0142] Alternatively, if the image server system 204 determines that the probability output by the generated statistical distribution is greater than the threshold, during step (K), the image server system 204 indicates that the end date 234 of the wildfire has been identified, assuming that the image server system 204 does not detect a wildfire for a predetermined number of days after the potential end date 234. As shown in system 200, the end date 234 of the wildfire corresponds to August 5, 2019. Step (K) of system 200 is similar to step (I) of system 100.

[0143] During stage (M), the image server system 204 provides, for output, the wildfire time range 236. The time range 236 indicates that the wildfire range is from June 1, 2019 to August 5, 2019. Stage (M) of system 200 is similar to stage (J) of system 100. For example, the image server system 204 can output the time range 236 to one or more external or internal pipelines.

[0144] FIG. 2B is a block diagram showing an example of a system 201 for generating a statistical distribution when determining the wildfire time range. System 201 shows the processes implemented during stages (D) and (H) from system 100 and stages (D) and (I) from system 200. Further, system 201 and its processes may also be implemented by the image server system 102.

[0145] In some implementations, system 201 represents a process for generating a statistical distribution. The image server system 204 can generate a statistical distribution, which, for example, is a Poisson distribution, a normal distribution, or a Gaussian distribution. The process for generating the statistical distribution generally includes, among other things, (i) identifying a first date that is three months before the input date, (ii) identifying a second date that is one year or nine months before the first date, (iii) selecting a subset of satellite images from the acquired satellite images based on the time range between the first date and the second date, (iv) determining the mean, standard deviation, and other statistical characteristics of the fire pixels from the subset of satellite images, and (v) generating a statistical distribution based on the statistical characteristics of the fire pixels from the subset of satellite images.

[0146] In some implementations, the image server system 204 can generate a statistical distribution without identifying a first date that is three months before the input date. In this case, if the image server system 204 determines that the input date corresponds to the actual start date of a wildfire, such as the start date 118 generated in the system 100, the image server system 204 can proceed to identify a second date that is one year before the input date without identifying the first date. For example, if the input date is the determined start date of a wildfire, such as June 1, 2019, instead of identifying a date three months before June 1, 2019 to ensure that there is no wildfire in the satellite image, the image server system 204 can identify a second date that is one year before the start date. This corresponds to the second date of June 1, 2018.

[0147] As a result, for example, if the image server system 204 moves the start date back by only three months, the image server system 204 can identify a time range from June 1, 2018 to June 1, 2019 instead of from March 1, 2018 to March 1, 2019. In some cases, the image server system 204 can identify a nine - month time range instead of a one - year time range, for example, from September 1, 2019 to June 1, 2019. The image server system 204 can identify a nine - month range when a shorter time range is required due to memory constraints, for example, to avoid detecting fire pixels in historical satellite images, or can identify a nine - month range when an external user requests that specific time range.

[0148] During step (A), the image server system 204 can determine a first date 242 that is three months before the input date. For example, if the input date of the image server system 204 corresponds to the input date 110 of a wildfire, such as July 5, 2019, the image server system 204 can determine that the first date 242 is April 5, 2019. In some cases, the image server system 204 skips this step if the input date corresponds to the determined start date of a wildfire, such as the start date 118.

[0149] During step (B), the image server system 204 can determine a second date 244 that is one year before the first date 242. For example, if the first date 242 corresponds to April 5, 2018 and the input date corresponds to the wildfire input date 110, the image server system 204 can determine that the second date 244 is April 5, 2019. However, in this example, if the input date is the start date 118, the image server system 204 may determine that the first date 242 is June 1, 2018.

[0150] During step (C), the image server system 204 can select a subset of satellite images from the acquired satellite images. As shown in system 201, the image server system 204 can obtain the location 240 of the geographic area where the wildfire occurred and the date 238 on which the wildfire occurred at location 240. The date can be, for example, a string indicating July 5, 2019, and the location can be a string or number indicating the latitude and longitude coordinates of 33.8121N, -117.91899E. This step is the same as steps (A) and (B) from system 100.

[0151] Next, the image server system 204 can request satellite images from the satellite image database 218 by providing the date 238, the location 240, and the period 237. The period 237 can indicate, for example, a period before the date 238 to obtain satellite images. For example, the period 237 can indicate a period of one year, three years, five years, or another period of time long enough to construct a statistical distribution.

[0152] In some implementations, the image server system 204 can indicate that the period 237 corresponds to a period before the date 228 and a period after the date 238. For example, if the image server system 204 is attempting to determine the end date of a wildfire, the image server system 204 can instruct the satellite image database 218 to identify two years before the date 238 and five months after the date 238. Other periods may also be indicated.

[0153] The satellite image database 218 can include satellite images showing various geographical regions of the Earth. For example, the satellite images can include high-resolution images 213b, noisy images 213a, and other types of images such as infrared videos and other media.

[0154] In some implementations, the image server system 204 can obtain a satellite image and select a subset of the satellite image from the obtained satellite image. For example, as shown in system 201, the image server system 204 can select the satellite image 213c from the obtained satellite image. The satellite image 213c can include a set of satellite images showing high-resolution images, noisy resolution images, low-resolution images, satellite videos, and other satellite media. The image server system 204 can select the satellite image 213c based on the periods identified in steps (A) and (B) of system 201, one or more time ranges that avoid fire pixel detection in the set of satellite images, and other criteria.

[0155] During stage (D), the image server system 204 can determine the detection of fire pixels for each day over the identified time range. This stage is similar to stage (D) from system 100. For example, the image server system 204 can analyze each satellite image from the satellite image 213c and determine the number of pixels that appear to indicate a wildfire for each day within the set of satellite images. For example, the image server system 102 can analyze the satellite image 113c for each day between April 5, 2018 and April 5, 2019 and determine the number of fire pixels for each day. In another example, the image server system 102 can analyze within the polygon of the satellite image 113c for each day between April 5, 2018 and April 5, 2019 and determine the number of fire pixels for each day within the polygon. The image server system 102 can, for example, count two fire pixels on April 5, 2018, count three fire pixels on April 6, and continue to count the satellite images for each day until April 5, 2019.

[0156] During stage (E), in response to determining the number of fire pixels for each day within the satellite image 113c, the image server system 204 can generate a statistical distribution. For example, the image server system 204 can generate one or more parameters regarding a statistical distribution that can be a Poisson distribution, such as the mean and variance of the distribution. If the statistical distribution is a Poisson distribution, the image server system 204 can determine the average number of pixels that appear to indicate a fire from the set of satellite images 113c. In this case, the average number of identified pixels that appear to indicate a wildfire over the identified time range can be, for example, 5, and this value is equivalent to the variance of the Poisson distribution. In response to identifying the average of the fire pixel detections within the satellite image and fitting that average, the image server system 204 can provide the statistical distribution 116 for various applications.

[0157] FIG. 3 is a flowchart showing an example of a process 300 for generating a time range of a wildfire. The image server system 102 of the system 100 and the image server system 204 of the system 200 can implement the process 300.

[0158] The image server system obtains (302) the date on which a fire occurred within a geographic area. For example, an external database such as a time database can provide the image server system with a date indicating the day on which a wildfire occurred in the geographic area. The date can be provided in a month, day, year format, or another format. The date can correspond to the start date of the wildfire, the end date of the wildfire, or another date between the start date and the end date of the wildfire.

[0159] In some implementations, the image server system can also obtain a location that describes the location where the wildfire occurred based on the date. For example, the location can include location GPS coordinates, the name of a landmark, the name of a city, the name of another geographic area, a specific address, or other locations.

[0160] The image server system can also obtain a polygon that indicates the area within the satellite image that encompasses the wildfire. The polygon can spatially limit the number of pixels within the satellite image that the image server system can search to identify fire pixels. In essence, the image server system can search for fire pixels within the satellite image within the area spatially defined by the polygon to reduce the processing and amount of pixels that the image server system needs to search to identify fire pixels.

[0161] The image server system obtains (304) a first satellite image of the geographic area before the date on which a fire occurred within the geographic area. In some implementations, the image server system can provide the obtained location that describes the geographic area where the wildfire occurred and the obtained date on which the wildfire occurred to the satellite image database. Additionally, the image server system can also provide a time range indicating a period before the input date to obtain the satellite image. The period can include, for example, one year before the input date, two years before the input date, five years before the input date, or some other period before the input date that is sufficient to construct a statistical distribution.

[0162] The satellite image database can use the obtained date, the obtained location, and the time range to identify satellite images that meet the provided criteria. The satellite images can include one or more satellite images, such as high-quality, medium-quality, low-quality, noisy, and other satellite images. The satellite images can show one or more geographic areas of the Earth. In some implementations, the satellite image database can provide the identified satellite images that meet the criteria to the image server system to construct a statistical distribution.

[0163] The image server system selects (306) a first set of images from the first satellite image before the date on which a fire occurred within the geographic area. In some implementations, the image server system can identify a first set of images from the first satellite image to construct a statistical distribution. First, the image server system can identify the period before the input date within the obtained satellite image that does not show a wildfire. Since a wildfire generally does not last longer than three months, the image server system can determine the date three months before the input date. By identifying the date three months before the input date, the image server system can safely assume that the same wildfire identified by the input date and location is not active or on fire in the corresponding satellite image.

[0164] In some implementations, the image server system can determine the date one year before the date that is three months before the input date. For example, when the input date corresponds to July 5, 2019, the image server system can determine that the date three months before the input date is April 5, 2019. Next, the image server system identifies the date one year before April 5, 2019, which corresponds to April 5, 2018. In some implementations, the image server system can use the date nine months before instead of the date one year before.

[0165] In some implementations, the image server system can use this time range to identify a first set of satellite images from the first satellite image to construct a statistical distribution. For example, the image server system identifies satellite images from the satellite image database of dates between April 5, 2018 and April 5, 2019 including the end values.

[0166] However, in order for the image server system to use the first set of satellite images from April 5, 2018 to April 5, 2019, the image server system can ensure that there are no historical fires in the satellite images identified during that period. For example, the image server system can make this determination using an external database of historical fires. If the external database of historical fires indicates that there were no fires during this time, the image server system can execute a fire detection algorithm on each satellite image within the time range from April 5, 2018 to April 5, 2019 to determine the number of pixels containing fire in each image. If the number of fire pixels in the satellite image is less than the threshold, the image server system can indicate that a particular satellite image does not contain fire. Alternatively, if the image server system finds that the image contains fire, for example, if the number of fire pixels is greater than the threshold, it can adjust the time range.

[0167] The image server system generates a first statistical distribution from a first set of images (308). To generate the first statistical distribution, the image server system can generate one or more parameters for the statistical distribution. For example, the image server system can determine the number of pixels that appear to indicate a fire in each day's satellite image identified from (306). The image server system can use a fire detection algorithm to count the number of fire pixels in each day. In some implementations, the image server system can crop a polygon for each of the images within the identified satellite image before counting the fire pixels to reduce the number of pixels that need to be analyzed. The image server system can then determine the average value or average number of fire pixels from each image. The image server system may also determine other data descriptors, such as standard deviation and variance, to fit a particular statistical distribution.

[0168] For example, the image server system can fit the average of the average number of fire pixels to a Poisson distribution. In a Poisson distribution, the average is equivalent to the variance. For other distributions, such as the normal distribution and the Gaussian distribution, it is necessary for the image server system to perform different processes to determine the data descriptors that help fit the identified satellite image to the other distributions. For example, when the data is fit to a Poisson distribution, the image server system can process the acquired satellite image to identify the start date of a wildfire.

[0169] The image server system determines the start date of a fire (310) based on a comparison between a first satellite image and a first statistical distribution. In some implementations, the generated statistical distribution can be used to indicate the probability that some event has occurred from a baseline of the generated statistical distribution. For example, the probability density function of a Poisson distribution can return the probability that a particular day with k counted pixels has occurred naturally from the distribution of noise. The lower the value output by the PDF, the higher the likelihood that an external force, such as a wildfire, contributed to the count of the k value. Alternatively, the higher the value output by the PDF, the lower the likelihood that an external force contributed to the count of the k value, indicating that the image is more closely similar to an image from the baseline distribution.

[0170] The image server system can identify a satellite image of a day before the date on which a wildfire occurred from the acquired satellite images. The image server system can count or determine the number of pixels in the satellite image from the previous day that appear to indicate a fire. In some cases, the number of pixels to be counted can be within a polygon region cropped by the image server system. The image server system can then provide the number of fire pixels determined for that image on that particular day as an input to the generated statistical distribution.

[0171] The image server system can compare the output probability from a generated statistical distribution, such as a Poisson distribution, with a threshold value. If the output probability is less than the threshold value, the image server system can determine that the corresponding satellite image includes the likelihood of a fire. Alternatively, if the output probability is greater than the threshold value, the image server system can determine that the corresponding satellite image does not include a fire. The image server system repeats this process if a fire is determined, going back in time, for example, from July 4, 2019 to July 3, 2019, until a satellite image that does not appear to indicate a wildfire is found.

[0172] In response to the image server system determining that the satellite image does not indicate a wildfire, the image server system obtains additional satellite images from the acquired satellite image for a predetermined number of days prior to a specific day. For example, if the image server system determines a potential start date of June 1, 2019, the image server system can identify eight days prior to June 1, 2019, for example, May 24, 2019, and obtain satellite images for each of those days. The image server system attempts to identify and verify whether June 1, 2019 is the actual start date, analyzes a predetermined number of days prior to its potential start date, and determines that there is no fire in the satellite images corresponding to those days. If there is no fire on those days, the image server system can assert with confidence that June 1, 2019 is the actual start date of the fire.

[0173] First, the image server system can count the number of pixels that appear to indicate a fire for each day in a predetermined number of days prior to June 1, 2019. Next, the image server system can use the statistical distribution and the number of pixels that appear to indicate a wildfire for each corresponding day to generate a likelihood for each day. The statistical distribution can return the probability or likelihood for each day. For example, for May 31, 2019, the probability could be 0.56, for May 30, 2019, the probability could be 0.6, and for May 29, 2019, the probability could be 0.7. This process is repeated until May 24, 2019, or until each day in the predetermined number of days has an associated probability. If the probability for each day is greater than a threshold, the image server system can indicate with confidence that June 1, 2019 is the actual start date of the fire. If one or more of the daily probabilities are less than the threshold, the image server system can continue to iterate in the reverse direction to find the actual start date of the wildfire and then find the entire week prior to the "no fire" days.

[0174] The image server system obtains (312) second satellite images of the geographical area before and after the determined start date on which a fire occurred within the geographical area. The image server system can provide the acquired location and the identified start date to the satellite image database. Additionally, the image server system can also provide a period around the identified start date for constructing a second statistical distribution, for example, a period of one year before the start date and three months after the start date of the satellite image for constructing a second statistical distribution and determining an end date. The satellite image database can identify and return a second satellite image that meets this criterion using a criterion. (312) includes functions similar to (304).

[0175] The image server system selects a second set of images from the second satellite images before the start date on which a fire occurred within the geographical area, and the second set of images is less than the first set of images (314). In some implementations, the image server system can identify a second set of images from the second satellite images for constructing a second statistical distribution. The image server system can identify a period before the start date within the acquired satellite images that does not indicate a wildfire. Since the date on which the fire occurred is already known, the image server system does not need to determine a date three months before the start date. Thus, the period before the start date for the second satellite images can be shorter than or less than the period identified for the first set of satellite images that included a three-month period before. Instead, the image server system can identify a date one year before the start date for constructing a second statistical distribution.

[0176] In some implementations, the image server system can use this time range to identify a second set of satellite images from a second satellite image in order to construct a second statistical distribution. For example, the image server system identifies satellite images from satellite image databases obtained between June 1, 2018 and June 1, 2019, including the end points. In addition, the image server system can ensure that there are no active wildfires in the second set of satellite images during the time range from June 1, 2018 to June 1, 2019. If there are active wildfires, the image server system can adjust the time range. (314) includes the same functions as (306).

[0177] The image server system generates a second statistical distribution (316) from a second set of images before the start date when a fire occurred within the geographical area. (316) includes the same functions as (308). In particular, the image server system can generate one or more parameters for the second statistical distribution. For example, the image server system can determine the number of pixels that appear to indicate a fire on each day of the satellite images identified from (314). The image server counts the number of fire pixels on each day using a fire detection algorithm and determines the average number of fire pixels from each image. The image server system may also determine other data descriptors, such as standard deviation and variance, in order to fit a specific statistical distribution, such as the Poisson distribution. When the data is fitted to a second statistical distribution such as the Poisson, the image server system can process the acquired satellite images to identify the end date of the wildfire.

[0178] The image server system determines the end date of the fire (318) based on a comparison between the second satellite image and the second statistical distribution that occurred after the start date. (318) includes the same functions as (310). In some implementations, the image server system can identify satellite images from satellite images acquired on days after the start date. The image server can count the number of fire pixels in the identified satellite image and provide the determined number of fire pixels as an input to the second statistical distribution. If the probability output from the second statistical distribution is less than the threshold, the image server system can determine that the corresponding satellite image contains the likelihood of a fire. Alternatively, if the output probability is greater than the threshold, the image server system can determine that the corresponding satellite image does not contain a fire. The image server system repeats this process, for example, from June 1, 2019 to June 2, 2019 to June 3, 2019, etc., one day at a time in the forward direction until a satellite that does not appear to indicate a wildfire is found.

[0179] In response to detecting a date as a potential end date, e.g., August 5, 2019, the image server system can obtain additional satellite images from the acquired satellite images for a predetermined number of days after the potential end date. Here, the image server system attempts to identify and verify whether August 5, 2019 is the actual end date, analyzes a predetermined number of days after the potential end date, and determines that there is no fire in the satellite images corresponding to those days. If there is no fire on those days, the image server system can assert with confidence that August 5, 2019 is the actual end date of the wildfire.

[0180] Similar to (310), the image server system can count the number of pixels that appear to indicate a wildfire on each day within a predetermined number of days after August 5, 2019. The image server system can use the second statistical distribution and the number of pixels that appear to indicate a wildfire on each corresponding day to generate the likelihood for each day. The statistical distribution can return the probability or likelihood for each day. If the probability for each day is greater than a threshold, the image server system can confidently indicate that August 5, 2019 is the actual end date of the fire. If one or more of the daily probabilities are less than the threshold, the image server system can continue to iterate in the forward time direction to find the actual end date of the wildfire and then find the entire next week of "no fire" days.

[0181] For output, the image server system provides a range that includes the start date and end date of the fire within the geographical area (320). In some examples, the time range of the wildfire, e.g., the determined start and end dates, can be provided to one or more other pipelines and also to the display of the image server system. Additionally, the image server system can provide the time range to the client device of the user who requested the time range via a network.

[0182] All embodiments and functional operations of the invention described in this specification can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed herein and their structural equivalents, or in combinations of one or more of them. Embodiments of the invention can be implemented as one or more computer program products, i.e., as one or more modules of computer program instructions encoded on a computer-readable medium for execution by, or to control the operation of, a data processing apparatus. The computer-readable medium can be a non-transitory computer-readable storage medium, a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter that causes a machine-readable propagated signal, or a combination of one or more of them. The term "data processing apparatus" encompasses all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the relevant computer program, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them. A propagated signal is an artificially generated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal generated to encode information for transmission to a suitable receiver device.

[0183] A computer program (also known as a program, software, software application, script, or code) may be written in any form of programming language, including compiled or interpreted languages, and may be deployed in any form, including as a stand-alone program or as part of a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program need not necessarily correspond to a file in a file system. The program may be stored in a portion of a file that holds other programs or data (such as one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (such as files that store one or more modules, subprograms, or portions of code). A computer program may be executed on one computer or deployed so as to be executed on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

[0184] The processes and logical flows described herein may be implemented by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logical flows may also be implemented by, for example, dedicated logic circuitry, such as an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit), and the apparatus may also be implemented as dedicated logic circuitry, such as an FPGA or an ASIC.

[0185] Processors suitable for the execution of a computer program include, by way of example, both general-purpose and special-purpose microprocessors, as well as any one or more processors of any kind of digital computer. Generally, a processor receives instructions and data from a read-only memory or a random access memory or both. Essential elements of a computer are a processor for executing instructions, and one or more memory devices for storing instructions and data. Generally, a computer also includes, or is operatively coupled to receive data from, or transfer data to, one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks. However, a computer need not have such devices. Further, a computer may be incorporated in another device, such as, by way of example only, a tablet computer, a cellular phone, a personal digital assistant (PDA), a mobile audio player, a Global Positioning System (GPS) receiver. Computer-readable media suitable for storing computer program instructions and data include, by way of example, semiconductor memory devices, such as EPROM, EEPROM, and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0186] To provide interaction with a user, embodiments of the present invention may be implemented on a computer, which has a display device for displaying information to the user, such as a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, and a keyboard and a pointing device (e.g., a mouse, a trackball) through which the user can provide input to the computer. Other types of devices may be used to provide interaction with the user. For example, the feedback provided to the user may be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback, and the input from the user may be received in any form, including acoustic, voice, or tactile input.

[0187] Embodiments of the present invention may be implemented in a computing system that includes back-end components (such as a data server), or middleware components (such as an application server), or front-end components (such as a client computer having a graphical user interface or a web browser through which a user can interact with an implementation of the present invention), or any combination of one or more such back-end, middleware, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication, such as a communication network. Examples of communication networks include a local area network ("LAN") and a wide area network ("WAN"), such as the Internet.

[0188] The computing system may include clients and servers. The clients and servers are generally separated from each other and typically interact through a communication network. The relationship between the clients and servers is created by computer programs that are executed on respective computers and have a client-server relationship with each other.

[0189] Although several implementations have been described in detail above, other modifications are possible. For example, the client application is described as accessing a delegate, but in other implementations, the delegate may be employed by other applications implemented by one or more processors, such as an application running on one or more servers. Additionally, the logic flows depicted in the figures do not require the specific order, or sequential order, shown to achieve the desired result. Additionally, other actions may be provided from, or actions may be removed from, the described flows, other components may be added to, or removed from, the described system. Accordingly, other implementations are within the scope of the following claims.

[0190] This specification includes details of many specific implementations, but these should not be construed as limiting the scope of any invention, or of what may be claimed, but rather as descriptions of features that may be specific to particular embodiments of a particular invention. Certain features described herein in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented separately in multiple embodiments, or in any suitable partial combination. Further, features may be described above as acting in a particular combination and as initially claimed as such, but one or more features from the claimed combination may, in some cases, be deleted from the combination, and the claimed combination may be directed to a sub-combination or variation of a sub-combination.

[0191] Similarly, the operations are depicted in the drawings in a particular order, but this should not be construed as requiring that such operations be performed in the particular order shown or in a sequential order, or that all of the illustrated operations be performed, to achieve the desired result. In certain circumstances, multitasking and parallel processing may be advantageous. Further, the separation of the various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the program components and systems described may generally be integrated together in a single software product or packaged into multiple software products.

[0192] Particular embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. For example, the actions recited in the claims can be performed in a different order and still achieve the desired result. As one example, the processes depicted in the accompanying drawings do not necessarily require the particular order shown, or a sequential order, to achieve the desired result. In certain implementations, multitasking and parallel processing may be advantageous.

Claims

1. A computer-implemented method to be implemented, comprising: obtaining, by a server, a date on which a fire occurred within a geographical area; obtaining, by the server, a first satellite image of the geographical area prior to the date on which the fire occurred within the geographical area; selecting, by the server, a first set of images from the first satellite image, wherein the first set of images is (i) captured prior to the date on which the fire occurred within the geographical area and (ii) does not indicate a fire that occurred within the geographical area; generating, by the server, a first statistical distribution indicating the likelihood of fire occurrence from the first set of images; determining, by the server, a start date of the fire based on a comparison between the first satellite image and the first statistical distribution; obtaining, by the server, a second satellite image of the geographical area before and after the determined start date on which the fire occurred within the geographical area; selecting, by the server, a second set of images from the second satellite image before the start date on which the fire occurred within the geographical area, wherein the quantity of the second set of images is less than the quantity of the first set of images; generating, by the server, a second statistical distribution indicating the likelihood of fire occurrence from the second set of images before the start date on which the fire occurred within the geographical area; determining, by the server, an end date of the fire based on a comparison between the second satellite image and the second statistical distribution that occurred after the start date; providing, for output by the server, a range including the start date of the fire and the end date of the fire within the geographical area. A computer-implemented method comprising the above steps.

2. obtaining, by the server, the date on which the fire occurred within the geographical area, where the date may correspond to the start date of the fire, the end date of the fire, or another date within the range obtaining, by the server, a location describing the geographical area The computer-implemented method according to claim 1, comprising: obtaining, by the server, the date on which the fire occurred within the geographical area, where the date may correspond to the start date of the fire, the end date of the fire, or another date within the range, and providing, by the server, the location describing the geographical area and the date on which the fire occurred to a satellite image database, and in response to providing the location and the date, obtaining, by the server, a first satellite image of the geographical area from a period prior to the date.

3. obtaining, by the server, a first satellite image of the geographical area prior to the date on which the fire occurred within the geographical area providing, by the server, the location describing the geographical area where the fire occurred and the date on which the fire occurred to a satellite image database The computer-implemented method according to claim 2, comprising: obtaining, by the server, a first satellite image of the geographical area from a period prior to the date in response to providing the location and the date.

4. selecting, by the server, a first set of the images from the first satellite image prior to the date on which the fire occurred within the geographical area identifying, by the server, a period for generating a first statistical distribution, where the period corresponds to a period prior to the date selecting, by the server, a first set of the images from the first satellite image based on the period determining, by the server, an indication as to whether one or more pixels from the first set of the selected images indicate a fire The server adjusts the first set of the selected images to exclude one or more images of the first set of the selected images that indicate the fire by comparing the one or more pixels indicating the fire with a threshold value. The computer-implemented method according to any one of claims 1 to 3 includes this.

5. Generating the first statistical distribution from the first set of the images is In response to adjusting the first set of the selected images, the server determines one or more parameters of the first statistical distribution The server determines the number of pixels that are likely to indicate a fire on each day of the first set of the images. The server determines the average of the number of pixels that are likely to indicate a fire on each day of the first set of the images. The computer-implemented method according to claim 4 includes generating the first statistical distribution by setting the determined average to the one or more parameters by the server.

6. Determining the start date of the fire based on the comparison between the first satellite image and the first statistical distribution is The server identifies a satellite image from the first satellite images corresponding to the days before the date on which the fire occurred. The server determines the number of pixels that appear to indicate a fire from the identified satellite image of the day. The server generates a likelihood that the satellite image from the first satellite image includes an indication of a fire based on the first statistical distribution and the determined number of pixels that appear to indicate a fire. The server compares the likelihood with a threshold value. In response to determining that the likelihood does not exceed the threshold, in order to determine the start date, the server obtains another satellite image from the first satellite image corresponding to another date before the date on which the fire occurred. The computer-implemented method according to any one of claims 1 to 5 includes this.

7. In response to determining that the likelihood for a particular day exceeds the threshold, the method obtains additional satellite images for a predetermined number of days before the particular day by the server, for each day of the predetermined number of days, determines the number of active fire pixels from the additional satellite image for that day by the server, generates a likelihood that the additional satellite image for that day does not contain an indication based on the first statistical distribution and the determined number of pixels that appear to indicate a fire by the server, and further includes determining that the day corresponding to the identified satellite image corresponds to the start date of the fire in response to the server determining that each day of the predetermined number of days does not indicate the fire. The computer-implemented method according to claim 6 includes this.

8. Obtaining the second satellite image of the geographical area before and after the determined start date on which the fire occurred within the geographical area is provided by the server with the location describing the geographical area where the fire occurred and the start date on which the fire occurred to a satellite image database, and in response to providing the location and the start date, obtaining the second satellite image showing the geographical area from a period before and after the start date by the server. The computer-implemented method according to any one of claims 1 to 7 includes this.

9. Selecting a second set of the images from the second satellite images prior to the start date on which the fire occurred within the geographical area, wherein the amount of the second set of the images is less than the amount of the first set of the images. Selecting the second set of the images is Identifying, by the server, a period for generating the second statistical distribution, wherein the period corresponds to a period prior to the start date. Identifying the period for generating the second statistical distribution Selecting, by the server, a second set of the images from the second satellite images based on the period Determining, by the server, whether one or more pixels from the selected second set of the images indicate a fire Adjusting, by the server, the selected second set of the images to exclude one or more images of the selected second set of the images that indicate the fire by comparing the one or more pixels indicating the fire with a threshold value. The computer-implemented method according to any one of claims 1 to 8 includes

10. Generating the second statistical distribution from the second set of the images prior to the start date on which the fire occurred within the geographical area In response to adjusting the selected second set of the images, by the server, one or more parameters of the second statistical distribution Determining, by the server, the number of pixels that are likely to indicate a fire on each day of the second set of the images Determining, by the server, the average of the number of the pixels that are likely to indicate a fire on each day of the second set of the images Generating the second statistical distribution by setting the determined average to the one or more parameters by the server. The computer-implemented method according to claim 9 includes generating by

11. Determining the end date of the fire based on a comparison between the second satellite image and the second statistical distribution that occurred after the start date, identifying, by the server, a satellite image from the second satellite images corresponding to a date after the start date, determining, by the server, the number of pixels that appear to indicate a fire from the identified satellite image of the date, generating, by the server, a likelihood that the satellite image from the second satellite image contains an indication of a fire based on the second statistical distribution and the determined number of pixels that appear to indicate a fire, comparing, by the server, the likelihood with a threshold, in response to determining that the likelihood exceeds the threshold, obtaining, by the server, another satellite image from the first satellite images corresponding to another date after the date on which the fire occurred to determine the end date, the computer-implemented method according to any one of claims 1 to 10.

12. In response to determining that the likelihood exceeds the threshold for a particular date, the method obtains, by the server, additional satellite images for a predetermined number of days after the particular date, for each day of the predetermined number of days, determines, by the server, the number of pixels from the additional satellite image of that day, generates, by the server, a likelihood that the additional satellite image of that day does not contain an indication based on the second statistical distribution and the determined number of pixels that appear to indicate a fire, in response to determining, by the server, that each day of the predetermined number of days does not indicate the fire, determines that the date corresponding to the identified satellite image corresponds to the end date of the fire, further comprising the computer-implemented method according to claim 11.

13. The computer-implemented method according to any one of claims 1 to 12, wherein the first statistical distribution and the second statistical distribution are different Poisson distributions.

14. A system comprising: one or more computers and one or more storage devices storing instructions, wherein when the instructions are executed by the one or more computers, the one or more computers are caused to obtain, by a server, a date on which a fire occurred within a geographic area; obtain, by the server, a first satellite image of the geographic area prior to the date on which the fire occurred within the geographic area; select, by the server, a first set of images from the first satellite image, the first set of images being (i) captured prior to the date on which the fire occurred within the geographic area and (ii) not indicative of a fire occurring within the geographic area; generate, by the server, a first statistical distribution indicative of the likelihood of fire occurrence from the first set of images; determine, by the server, a start date of the fire based on a comparison of the first satellite image and the first statistical distribution; obtain, by the server, a second satellite image of the geographic area before and after the determined start date on which the fire occurred within the geographic area; select, by the server, a second set of images from the second satellite image before the start date on which the fire occurred within the geographic area, the amount of the second set of images being less than the amount of the first set of images; generate, by the server, a second statistical distribution indicative of the likelihood of fire occurrence from the second set of images before the start date on which the fire occurred within the geographic area; The server determines the end date of the fire based on a comparison between the second satellite image and the second statistical distribution that occurred after the start date. The system performs operations including providing, for output by the server, a range including the start date of the fire and the end date of the fire within the geographical area.

15. Obtaining the date on which the fire occurred within the geographical area. The server obtains a location describing the geographical area. The server obtains the date on which the fire occurred within the geographical area, where the date may correspond to the start date of the fire, the end date of the fire, or another date within the range. The system according to claim 14 includes obtaining the date on which the fire occurred within the geographical area.

16. Obtaining the first satellite image of the geographical area before the date on which the fire occurred within the geographical area. The server provides to the satellite image database the location describing the geographical area where the fire occurred and the date on which the fire occurred. In response to providing the location and the date, the server obtains the first satellite image showing the geographical area from a period before the date. The system according to claim 15 includes obtaining the first satellite image showing the geographical area from a period before the date.

17. Selecting a first set of the images from the first satellite image before the date on which the fire occurred within the geographical area. The server identifies a period for generating the first statistical distribution, where the period corresponds to a period before the date. The server identifies the period for generating the first statistical distribution. The server selects the first set of the images from the first satellite image based on the period. The server determines whether one or more pixels from the selected first set of images indicate a fire; The server adjusts the selected first set of images to exclude one or more images from the selected first set of images that indicate a fire by comparing the one or more pixels indicating a fire to a threshold. The system according to any one of claims 14 to 16.

18. Generating the first statistical distribution from the first set of images; In response to adjusting the selected first set of images, the server determines one or more parameters of the first statistical distribution; The server determines the number of pixels in each day of the first set of images that are likely to indicate a fire; The server determines the average of the number of pixels in each day of the first set of images that are likely to indicate a fire; The system according to claim 17, wherein the server generates the first statistical distribution by setting the determined average as the one or more parameters.

19. Based on the comparison between the first satellite image and the first statistical distribution, the server determines the start date of the fire; The server identifies a satellite image from the first satellite images corresponding to days before the date on which the fire occurred; The server determines the number of pixels that appear to indicate a fire from the identified satellite image of the day; The server generates a likelihood that the satellite image from the first satellite images contains an indication of a fire based on the first statistical distribution and the determined number of pixels that appear to indicate a fire; The server compares the likelihood to a threshold; In response to determining that the likelihood does not exceed the threshold, in order to determine the start date, the server obtains another satellite image from the first satellite image corresponding to another date before the date on which the fire occurred, the system according to any one of claims 14 to 18, including this.

20. A non-transitory computer-readable medium storing software including instructions executable by one or more computers, the instructions, when executed, causing the one or more computers to, obtain, by a server, the date on which a fire occurred within a geographic area; obtain, by the server, a first satellite image of the geographic area before the date on which the fire occurred within the geographic area; select, by the server, a first set of images from the first satellite image, the first set of images being (i) captured before the date on which the fire occurred within the geographic area and (ii) not indicating a fire that occurred within the geographic area; generate, by the server, a first statistical distribution indicating the likelihood of fire occurrence from the first set of images; determine, by the server, the start date of the fire based on a comparison between the first satellite image and the first statistical distribution; obtain, by the server, second satellite images of the geographic area before and after the determined start date on which the fire occurred within the geographic area; select, by the server, a second set of images from the second satellite image before the start date on which the fire occurred within the geographic area, the amount of the second set of images being less than the amount of the first set of images; generate, by the server, a second statistical distribution indicating the likelihood of fire occurrence from the second set of images before the start date on which the fire occurred within the geographic area; The server determines the end date of the fire based on a comparison between the second satellite image and the second statistical distribution that occurred after the start date; A non-transitory computer-readable medium that causes the server to perform operations including providing a range including the start date of the fire and the end date of the fire within the geographical area for output by the server.

Images