Terrain-based automatic detection of well sites and their surroundings

Abstract

Aspects of the invention include detecting a first wellsite at a first location using a first machine learning model based at least in part on a first data set comprising spectral data describing gas emissions from the first location. Detecting an environmental event within a threshold distance of the wellsite. Determining a probability of damage to the first wellsite from the environmental event.

Description

Technical Field

[0001] The present invention generally relates to computer-based detection systems, and more specifically to the automated detection of well pads and their surrounding environment based on terrain under operating conditions. Background Technology

[0002] Pad drilling is a drilling technique in which multiple wellbores are drilled from a single, compact platform called a well site. A wellbore is a hole that defines an oil well. A well site is a section of land cleared for a drilling rig to drill wellbores. A well site typically spans four to five square acres and can include any number of oil wells. Pad drilling uses a combination of vertical and horizontal drilling. The drilling rig drills the wellbore straight down into the ground, and once the wellbore reaches a certain depth, the rig drills horizontally in any given direction. Once the drilling rig has completed drilling, an oil rig is placed to extract any oil from the ground. The oil extraction process requires specialized equipment, including oil rigs, protective barriers, and storage tanks. Summary of the Invention

[0003] Embodiments of the present invention relate to terrain-based automated detection of well sites. A non-limiting example computer-implemented method includes: detecting a first well site at a first location using a first machine learning model, at least in part based on a first dataset comprising spectral data describing gas emissions from a first location; detecting environmental events within a threshold distance of the well site; and determining the probability of damage to the first well site from the environmental events.

[0004] According to an embodiment, the environmental event is a fire, landslide, or flood.

[0005] According to an embodiment, the computer-implemented method includes the step of predicting a suitable location for a second well site at the second location, based at least in part on the similarity between the terrain of the second location and that of the first location. The computer-implemented method also includes the step of predicting the probability of damage caused by environmental events at the second location.

[0006] According to an embodiment, the computer-implemented method further includes using a second machine learning model to extract features from a first dataset to determine the terrain at a location.

[0007] According to an embodiment, the computer-implemented method further includes encoding data, at least in part, based on terrain, to delineate the boundaries of potential well sites.

[0008] According to an embodiment, a first machine learning model determines whether a bounded potential well site is a source of gas emissions.

[0009] According to one embodiment, the computer-implemented method further includes determining the identity, composition, and volume of the gas emissions, and comparing the emissions with regulation requirements.

[0010] Other embodiments of the present invention implement the features of the above-described method in computer systems and computer program products.

[0011] Additional technical features and advantages are achieved through the technology of this invention. Embodiments and aspects of the invention are described in detail herein and are considered part of the claimed subject matter. For a better understanding, refer to the detailed description and accompanying drawings. Attached Figure Description

[0012] The details of the exclusive rights described herein are specifically pointed out and explicitly claimed in the claims at the end of the specification. The foregoing and other features and advantages of embodiments of the invention will become apparent from the following detailed description taken in conjunction with the accompanying drawings, in which:

[0013] Figure 1 A block diagram of components of a well site detection system according to one or more embodiments of the present invention is shown;

[0014] Figure 2A These are images from an aviation source depicting multiple potential well sites; Figure 2B It is an enlarged image depicting a single well site, including well site-related features;

[0015] Figure 3A A map depicting the well site boundaries shown is provided according to one or more embodiments of the present invention. Figure 3B The well site boundaries according to one or more embodiments of the present invention are depicted without visible light images;

[0016] Figure 4 A flowchart of a process for well site inspection according to one or more embodiments of the present invention is shown;

[0017] Figure 5 A cloud computing environment according to one or more embodiments of the present invention is described;

[0018] Figure 6 An abstract model layer according to one or more embodiments of the present invention is described; and

[0019] Figure 7 A block diagram is depicted for a computer system for implementing one or more embodiments of the present invention.

[0020] The figures depicted herein are illustrative. Many variations of the figures or operations described herein are possible without departing from the spirit of the invention. For example, actions may be performed in a different order, or actions may be added, deleted, or modified. Furthermore, the term "coupled" and its variations describe a communication path between two elements and do not imply a direct connection between elements without an intervening element / connection. All such variations are considered part of the specification. Detailed Implementation

[0021] One or more embodiments of the present invention provide systems and methods for using machine learning techniques on spatially correlated images to identify physical structures to identify well sites and assess the risks of floods, wildfires, and landslides to these well sites.

[0022] Commercial businesses and regulatory agencies need accurate information about the number and location of well sites to determine emission levels and accurately assess risks. Current regulations require well site operators to cease operations in the event of certain environmental events, such as floods, landslides, and wildfires in the area surrounding the well site. In the event of a flood, landslide, or wildfire, regulatory agencies must verify that operators have ceased operations at nearby well sites.

[0023] Therefore, the ability to remotely detect hazardous environmental events near well sites and calculate the distance between the center of such events and any nearby well sites is desired. It is also desirable to calculate the rate at which environmental events approach any well site and the time of arrival to provide early warnings to well site operators. Conventional computer-based detection systems rely on photographic images composed of red, green, and blue (RGB) bands for object classification using machine learning algorithms. However, these machine learning algorithms are often trained on outdated and inaccurate training data. Information is often provided in different formats depending on the source, which can lead to high error tolerances.

[0024] One or more embodiments of the present invention address one or more of the aforementioned drawbacks by providing methods and systems for identifying well sites using a combination of spectral image data to detect terrain, oil production equipment, and gas emissions. Spectral information extracted from satellites can also be used to detect infrared or high-temperature features, which can indicate wildfires, floods, and landslides. The methods and systems described herein further generate real-time and current training data to train machine learning units for identifying well sites and any nearby environmental conditions.

[0025] Now go to Figure 1Well site detection system 100 is generally shown according to one or more embodiments of the present invention. Well site detection system 100 includes a data preprocessing unit 102, a terrain detection unit 104, and a well site detection unit 106. Well site detection system 100 is also operable to exchange data with at least one sensor 108 and at least one database 110 via a communication network 112. Sensor 108 may be attached to a satellite, aircraft, balloon, unmanned aerial vehicle (UAV), or other aerial source. Database 110 may be any storage device containing data describing a piece of land.

[0026] Data preprocessing unit 102 receives data describing a land parcel and prepares the data for analysis by terrain detection unit 104 and well site detection unit 106. Data preprocessing unit 102 can receive data from multiple sources and is operable to organize the received data regardless of the source. The data may include satellite imagery, spectral imagery, digital maps, or other data describing a land parcel. The data may be organized based on, for example, one or more of the following: location, acquisition time, changes detected based on reference images, proximity to environmental events, oil production levels, detected gas levels, or other suitable criteria. Data preprocessing unit 102 includes a normalization unit 114 for normalizing data from different sources (i.e., different sensors 108 and database 110). Data preprocessing unit 102 also includes a feature extraction unit 116 for extracting specific features from the data, such as terrain-related features, well site-related features, and environmental event-related features. For example, the terrain of a well site typically includes flat rectangular portions of land with little vegetation and the distribution of drilling equipment. The feature extraction unit 116 can extract features indicative of these properties from data (including spectral features and / or satellite imagery). The feature extraction unit 116 can also extract features describing the surrounding environment, such as the type of vegetation and natural structures including mountains, caves, and bodies of water.

[0027] In some instances, one or more of these features may be associated with areas that do not include well sites. Therefore, to distinguish between terrain that may include well sites and terrain that does not, feature extraction unit 116 can also identify features that can be associated with other terrain. Feature extraction unit 116 may further utilize metadata to encode data to indicate whether a feature indicates terrain with or without well sites. Feature extraction unit 116 can also extract features that indicate terrain similar to well site terrain but does not include well sites. For example, some agricultural settings include one or more features associated with well site terrain but do not include any well sites. Therefore, feature extraction unit 116 can extract features associated with crops or farm-related structures. This information can be used to allow terrain detection unit 104 and well site detection unit 106 to distinguish between well site terrain and other terrain.

[0028] The data preprocessing unit 102 further includes a data augmentation unit 118. Training machine learning units typically requires large datasets. The data augmentation unit 118 creates new data points / images by manipulating the original data. For example, the data augmentation unit 118 may receive image data and create multiple modifications to the images to increase the size of the training data. Modifications may include generating a mirror image, rotating the image, changing the color, cropping the image, scaling the image, or other modifications. The modified images are then appended to the original dataset to create a larger dataset for training the terrain detection unit 104 and the well site detection unit 106. The data augmentation unit 118 may use various augmentation techniques, such as geometric transformations, color space augmentation, kernel filters, image blending, random erasure, feature space augmentation, adversarial training, generative adversarial networks (GANs), neural style transfer, and meta-learning.

[0029] The terrain detection unit 104 can receive data from the data preprocessing unit 102 and analyze the data for terrain features indicating a well site. The terrain feature extraction unit 120 detects features of the terrain indicating a potential well site. The terrain neural network model 122 analyzes the features indicating the terrain to characterize the terrain (i.e., flat or rough, vegetated or unvegetated, boundaries, natural features, etc.). The terrain neural network model 122 can also track changes in the terrain from historical snapshots or images. Snapshots are considered “baselines,” and the terrain neural network model 122 can identify such changes occurring from the baseline in both space and time. These changes can be new buildings, new equipment, changes in land use, changes in vegetation, vegetation type, and water level. By detecting changes, the terrain detection unit 104 can determine whether any change indicates a well site. For example, road construction can indicate a road for building a well site.

[0030] When classifying the terrain of an unanalyzed land area, the terrain feature extraction unit 120 receives data from the data preprocessing unit 102 and the geospatial-temporal data platform 124. The geospatial-temporal data platform 124 includes a data repository containing maps, satellite imagery, weather drone data, and sensor-based device data. The data from both the terrain feature extraction unit 120 and the geospatial-temporal data platform 124 may pertain to a specific land area. Data received from the geospatial-temporal data platform 124 is used to augment the data received from the data preprocessing unit 102. The terrain feature extraction unit 120 processes the augmented data and extracts any terrain-related features.

[0031] The terrain neural network model unit 122 can receive extracted features from the terrain feature extraction unit 120 and process the information to classify the terrain of the land. Terrain can be a topology describing the height of, for example, land, vegetation, and man-made structures (roads, buildings, infrastructure). Terrain can also include the proximity of a location on the land to any other features, such as rivers, roads, mountains, and buildings. The terrain neural network model unit 122 can analyze data storing terrain information (e.g., raster or bitmap images) to determine whether a location has terrain that may be associated with a well site.

[0032] Based on this data, the terrain neural network model unit 122 can determine the characteristics of a piece of land, such as slope, the presence of gases, and vegetation type. For example, the slope of the terrain can be determined by looking at the difference between the values ​​of two adjacent pixels in the image data. If the difference is zero, the terrain is flat. However, if the difference is positive, the slope is tilted towards the first pixel used to calculate the difference, while a negative slope indicates that the terrain can tilt towards the second pixel. By examining spectral image data, the terrain neural network model unit 122 can identify gases and create a density map of gas concentrations on a piece of land. Moreover, the terrain neural network model unit 122 can detect vegetation by comparing the spectral characteristics from the image with vegetation indices (e.g., normalized differential vegetation index). When sunlight shines on different vegetation, the vegetation will absorb some wavelengths and reflect others. Vegetation cell structures have evolved to reflect near-infrared (NIR) wavelengths of light, while chlorophyll, or plant pigments, absorb visible light wavelengths. Therefore, if the terrain feature extraction unit 120 determines that a portion of an image displays a higher percentage of infrared light than visible light, it can classify that portion as dense vegetation with contrasting sparse vegetation. The terrain neural network model unit 122 can also identify environmental events such as floods, landslides, or wildfires. For example, the terrain neural network model unit 122 can receive time-series data and determine that the location of an identified fire or water has changed and is moving in direction. In other instances, the terrain neural network model unit 122 can analyze time-series data and determine that the location of an object (i.e., rocks, trees, or buildings) is moving in the same direction and determine that a landslide has occurred.

[0033] The terrain neural network model unit 122 can identify a portion of land as a potential well site location based on terrain characteristics. The terrain neural network model unit 122 performs identification based in part on the characteristics of terrain with pre-identified well sites. For example, the pre-identified well site terrain generally includes a portion of land characterized as a geometry without vegetation, and the size of this geometry is within a threshold of the average geometry region surrounding the unvegetated well site. The terrain neural network model unit 122 can identify this terrain as a potential well site location. After determining the potential locations of the well sites described by the data, the terrain neural network model unit 122 can encode the data to segment the potential locations of the well sites. The boundaries can be in a machine-readable form of code. The code can also guide the well site detection system 100 to use, for example... Figure 3A and 3B The shown boundaries of potential well sites are used to enhance any image of the land. The terrain neural network model unit 122 can then label the segmented image to identify the location of each potential well site in that area.

[0034] In addition to delineating boundaries for potential well sites, the terrain neural network model unit 122 can classify objects in the terrain surrounding each potential well site. For example, using spectral images, data from a geospatial-temporal data platform, and vegetation indexing, the terrain neural network model unit 122 can classify the density or type of vegetation around each potential well site. The terrain neural network model unit 122 can also identify other objects near potential well sites. For example, using data provided by the geospatial-temporal data platform 124, the terrain neural network model unit 122 can identify and determine proximity to other locations such as mountains, water, or cities. The terrain neural network model unit 122 can further determine the probability that a well site is near each identified vegetation, object, and / or has a specific terrain profile. In the analysis, the distance between the location of a potential well site and objects is calculated based on line of sight. This calculation is performed to identify the closest potential well sites in the area and detect differences or similarities between them.

[0035] For example, in many cases, a minimum distance is maintained between two well sites, which is determined by the lateral extent of the pipeline used to extract oil from the ground. Based on geospatial records, the orientation and length of any pipeline are combined with the distance between the location of the potential well site and the location of a pre-identified well site to determine whether the location of the potential well site is beyond the minimum distance from the pre-identified well site.

[0036] The terrain neural network model unit 122 can analyze the area surrounding a potential well site location to detect any environmental events that may be harmful to the well site, such as tornadoes, hurricanes, fires, or floods. Upon detection of an environmental event, the terrain neural network model unit 122 further analyzes time-series data to determine the rate at which the environmental event approaches the potential well site location. The terrain detection unit 104 is further operable to determine a threshold safe distance between the environmental event and the potential well site location.

[0037] The terrain neural network model unit 122 can also predict whether a portion of land without a well site is suitable for use as a well site. For example, if the probability that an identified well site has one or more specific features (i.e., flat topography, proximity to a specific type of vegetation, and proximity to other identified well sites) is greater than a threshold, the terrain neural network model unit 122 can identify land without a well site but possessing these features as potential well site locations. The terrain neural network model unit 122 can also rank potential locations based on their features. For example, each terrain-related feature can be provided with a score reflecting the probability of its association with a well site. Based on this score, the terrain neural network model unit 122 is able to rank a location as more likely to be used as a well site than another location. The terrain neural network model unit 122 can assign each feature, from which a suitable or unsuitable well site location is indicated, and assign a probability score to the feature. Each probability score is an expression of the likelihood that the feature is associated with the terrain of the well site. Each probability score can be further weighted based on whether the terrain neural network model unit 122 identifies a combination of two or more features that would make the location more or less suitable for a well site.

[0038] Well site detection unit 106 receives data from terrain detection unit 104 to determine whether the location of a potential well site includes an actual well site. Well site detection unit 106 includes multiple machine learning models for multi-scale object detection. Well site detection unit 106 may select a machine learning model based on identified terrain features. For example, well site detection unit 106 may use Region Convolutional Neural Network (R-CNN) model unit 126. R-CNN model unit 126 receives data from the terrain detection unit and determines whether the terrain includes a well site. In some embodiments of the invention, R-CNN 126 first generates bounding boxes in the image received from the terrain detection unit and runs a classifier on each bounding box. When classifying different objects, R-CNN model unit 126 removes duplicate categories and re-scores the bounding boxes based on other detected objects in the image. In other embodiments of the invention, well site detection unit 106 may also use You Only Look Twice (YOLT) model unit 128. YOLT model unit 128 increases the image sampling rate by using a sliding window to help find small, densely packed objects in the image. Furthermore, YOLT's neural network architecture is distinguishable from other neural networks by including denser final convolutional layers. In other embodiments of the invention, the well site detection unit 106 may also use a Single Shot Detector (SSD) model unit 130. The SSD model unit 130 includes a backbone model and an SSD head. The backbone model is an image classification neural network used to extract features. The SSD head includes one or more convolutional layers added to the ends of the backbone model neural network.

[0039] Well site detection unit 106 selects an appropriate neural network model based on the terrain features determined by terrain detection unit 104. Well site detection unit 106 uses the appropriate neural network model to analyze the location of potential well sites to determine the presence of actual well sites. Well site detection unit 106 can compare any detected gas with gases associated with well sites. Gases have their own spectral characteristics and will reflect electromagnetic waves of specific frequencies and wavelengths. For example, methane or carbon dioxide are gases commonly emitted from well sites. Therefore, the presence of a gas can indicate that the location of a potential well site actually includes the actual well site.

[0040] Well site detection unit 106 can take into account the movement of gas due to wind, temperature gradients, or other phenomena. Well site detection unit 106 can apply a fluidics model to the gas data to interpret turbulence from the wind, which can spatially extend into a plume and also dissolve concentrations. This plume dispersion can extend across the image, and the neural network is informed about the extent, shape, and expected concentration. Based on the application of one or more models, well site detection unit 106 can then identify the gas source to help determine whether a piece of land includes a well site.

[0041] The well site detection unit 106 can further use an appropriate neural network model to compare the machines and equipment detected at the location with those associated with the well site. For example, the well site detection unit 106 can detect the presence of pipelines, oil drilling rigs, gas container trucks, and other equipment and machinery to determine whether the location includes a well site. In some cases, if there is sufficient gas in the air, the spectral characteristics of the gas can overwhelm visible light data, revealing the physical structures beneath the gas. Therefore, the well site detection unit 106 can use an appropriate neural network model to analyze the time series of images of the potential location to determine the presence of any physical structures at the potential well site.

[0042] Well site detection unit 106 can also determine the probability of environmental events affecting the well site. For example, well site detection unit 106 uses an appropriate neural network model to analyze terrain data to predict the probability that a location will be affected by an environmental event. For example, how likely is a location to be affected by a landslide? Well site detection unit 106 can also analyze the speed of wildfires to determine whether the well site is at risk from wildfires. Well site detection unit 106 is further operable to use natural language processing techniques to analyze historical data (such as weather reports, electronic news articles, and other information) to optimize predictions. Well site detection unit 106 can use an appropriate neural network model and apply data to predict the probability that a well site will be damaged by an environmental event, and also predict whether locations without well sites will be affected by environmental events. In this sense, well site detection unit 106 can help determine the suitability of a portion of land as a well site location.

[0043] In response to the determined location, including the actual well site, the well site detection unit 106 can also alert the well site operator in response to environmental event data. Based on the speed of the environmental event and the minimum safe threshold distance, the well site detection unit 106 can send an alarm to the well site operator, including a description of the environmental event, the speed of the environmental event, and the maximum time that can be used to stop operations at the well site before the environmental event exceeds the minimum safe threshold distance. The minimum safe threshold distance can be changed based on the environmental event and the terrain.

[0044] The well site detection unit 106 can further use an appropriate neural network model to determine whether the well site complies with existing regulations, including any shutdown orders from the management agency. The well site detection unit 106 receives the identity and composition of any emitted gases from the well site as data and compares these values ​​with thresholds established through adjustments to determine whether the well site complies with applicable emission standards. This includes detecting the presence and level of gas emissions after a shutdown order to determine whether the well site has responded by shutting down in accordance with the order.

[0045] Sensor 108 can be any sensor operable to collect data for spectroscopy. Spectroscopy involves investigating and measuring data from portions of the electromagnetic spectrum. Sensor 108 may, for example, include a remote imaging sensor, such as a Medium Resolution Imaging Spectroradiometer (MODIS) or a Visible Infrared Imaging Radiometer Suite (VIIRS), or a Light Detection and Ranging System (LIDAR) acquiring spectral data at different wavelengths. Sensor 108 may further include a gas imager sensitive to infrared spectral bands to detect chemical plumes that can be generated by oil and gas operations. Spectral bands are electromagnetic signals along different ranges of the electromagnetic spectrum. Examples of chemical plumes include methane (CH4), a gas escaping from the well site; sulfur dioxide (SO2), a natural byproduct of oil and gas; and nitrogen dioxide (NO2), a gas released from pumps and compressors at the well site. Spectral bands can be used to detect the spectral characteristics of the corresponding gases. The spectral range of the sensor can be configured to include the spectral characteristics of any chemical species of interest.

[0046] The well site detection system 100 receives data from sensors 108 or a database 110 and analyzes the data to identify well sites. The data can be retrieved in real time as the sensors 108 pass over the land parcel, or the data can be previously stored in the database 110. The well site detection system 100 can also be operated to receive data from third parties, such as companies operating the well sites, municipal tax authorities, management agencies, or insurance companies.

[0047] The communication network 112 may include the Internet, fiber optic, microwave, xDSL (digital subscriber line), wireless local area network (WLAN) technology, satellite, wireless cellular technology, Bluetooth technology and / or any other suitable communication technology.

[0048] The phrases "neural network" and "machine learning" broadly describe the functionality of electronic systems that learn from data. Machine learning systems, engines, or modules may include machine learning algorithms, which can be trained, for example, in an external cloud environment (e.g., cloud computing environment 50), to learn a functional relationship between currently unknown inputs and outputs. In one or more embodiments, the machine learning functionality may be implemented using a terrain neural network model unit 122 with the ability to be trained to perform currently unknown functions. In machine learning and cognitive science, neural networks are a family of statistical learning models inspired by the biological neural networks of animals (and particularly the brain). Neural networks can be used to estimate or approximate systems and functions that depend on a large number of inputs.

[0049] The terrain neural network model unit 122 can be implemented as a so-called "neuromycomorphic" system of interconnected processor elements that act as simulated "neurons" and exchange "messages" with each other in the form of electronic signals. Similar to the so-called "plasticity" of synaptic neurotransmitter connections that transmit messages between biological neurons, the connections in the terrain neural network model unit 122 that transmit electronic messages between simulated neurons are provided with numerical weights corresponding to the strength or weakness of a given connection. During training, the weights can be adjusted and tuned empirically so that the terrain neural network model unit 122 adapts to the inputs and is able to learn. After weighting and transformation by a function determined by the network designer, the activation of these input neurons is then passed to other downstream neurons, often referred to as "hidden" neurons. This process is repeated until an output neuron is activated. The activated output neuron determines which character was read.

[0050] Figure 2A It is an image describing the distribution of well sites 200 and 202 across the region. Figure 2B This is a magnified image of a single well site, 204. (Example) Figure 2B As depicted, well site 204 has a generally rectangular shape and is adjacent to road 206. Well site 204 has generally flat terrain with little vegetation and is surrounded by protective fencing 208. Storage tank 212 is located on top of the well site, and extraction point 214 is designated at the center of well site 204. Contamination sources can arise above or between any of these features, with a probability distribution across the well site.

[0051] Figure 3AA boundary demarcation map 300 is depicted, generated from data collected by sensor 108. The boundary demarcation map 300 may include one or more aerial images, such as satellite images or autonomous aircraft images. In some embodiments, sensor 108 includes a light detection and ranging (LIDAR) system that measures the distance to a target (e.g., land) by illuminating it with a laser. The boundary demarcation map 300 can be generated from one or more satellite images of a specific geographic area over a predetermined time span. Each detected well site 302 includes a boundary depicted on the boundary demarcation map 300. Figure 3B Well site boundaries are depicted from boundary demarcation maps 300 that do not contain ground surface images. Each boundary demarcation has a polygonal shape and depicts the outer perimeter of the well site or the outer perimeter of multiple adjacent well sites.

[0052] Reference Figure 4 A flowchart illustrating a process for well site detection according to one or more embodiments of the present invention is shown. At box 202, the well site detection system receives data associated with a piece of land. The land may include one or more well sites. Data may be received from one or more sources, including aerial sources or databases. At box 404, the well site detection system selects any geospatial data from the data analyzed for this piece of land. Geospatial data refers to any data related to the characteristics of a piece of land. This includes data describing the surface contours of the land, any structures, pre-identified well sites, equipment, or other man-made objects on the land. Geospatial data also includes any data describing the surrounding terrain, including proximity to mountains, valleys, bodies of water, and other natural locations. At box 406, the well site detection system applies a machine learning model to the data to determine terrain-related features of the land. Before feeding the data to the machine learning model, at box 408, the well site detection system preprocesses the data, if not previously so. The well site detection system further annotates the data with boundaries that identify each portion of the land as a potential well site. In box 410, the well site detection system applies a terrain-specific machine learning model to the data to classify each potential well site as either included or excluded. In box 412, well site detection provides any additional preprocessing to the data. The terrain-specific machine learning model analyzes the data to determine if any gas associated with the well site is being emitted from any bounded area. The terrain-specific machine learning model also analyzes the data to determine if any machinery or equipment associated with the well site is found within any bounded area. In box 414, the well site detection system annotates the data regarding whether the bounded area includes or excludes the well site. If any gas is identified, the well site detection system determines the gas volume and emission rate based on time-series data. The well site detection system then compares the gas identification and gas volume with any applicable emission standards or shutdown orders.

[0053] The well site monitoring system is further operable to assist in any reduction of emitted gas volumes within or above emission standard thresholds. The system also analyzes the composition of gases above the well site and calculates the mixing ratios between different gases, such as methane release from leaks and nitrogen dioxide release through operational equipment. Based on this comparison, the system can generate a report disclosing gas emissions and applicable emission standards. The system can also remotely establish communications based on gas emissions and any applicable emission standards to guide entities to control any oil rig by slowing it down, accelerating it, or disabling it. Furthermore, the system can remotely establish communications with another aircraft or satellite to change its course to collect follow-up data to verify the findings or determine whether gas emissions have been reduced below emission standards or in accordance with shutdown instructions.

[0054] It is understood that while this disclosure includes a detailed description of cloud computing, implementations of the teachings cited herein are not limited to cloud computing environments. Rather, embodiments of the invention can be implemented in conjunction with any other type of computing environment now known or developed hereafter.

[0055] Cloud computing is a service delivery model that enables convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processing, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal management effort or interaction with service providers. This cloud model may include at least five features, at least three service models, and at least four deployment models.

[0056] The features are as follows:

[0057] On-demand self-service: Cloud consumers can unilaterally and automatically provide computing power, such as server time and network storage, as needed, without requiring human interaction with the service provider.

[0058] Extensive network access: Capabilities are available through networks and accessed via standard mechanisms that facilitate the use of heterogeneous thin client or thick client platforms (e.g., mobile phones, laptops, and PDAs).

[0059] Resource pooling: A provider's computing resources are pooled to serve multiple consumers using a multi-tenant model, where different physical and virtual resources are dynamically allocated and reallocated as needed. There is a sense of location independence because consumers typically do not have control or knowledge of the exact location of the resources provided, but are able to specify the location at a higher level of abstraction (e.g., country, state, or data center).

[0060] Rapid flexibility: The ability to provide capacity quickly and flexibly, automatically scaling down and up rapidly in some situations to scale up rapidly. For consumers, the available supply capacity often appears unlimited and can be purchased in any quantity at any time.

[0061] Measuring services: Cloud systems automatically control and optimize resource usage by leveraging metering capabilities at a specific level of abstraction appropriate to the service type (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported, providing transparency to both service providers and consumers.

[0062] The service model is as follows:

[0063] Software as a Service (SaaS): This provides consumers with the ability to use the provider's applications running on cloud infrastructure. Applications can be accessed from different client devices via a thin client interface such as a web browser (e.g., web-based email). Consumers do not manage or control the underlying cloud infrastructure, including the network, servers, operating system, storage, or even individual application capabilities, with possible exceptions such as limited user-specific application configuration settings.

[0064] Platform as a Service (PaaS): This provides consumers with the ability to deploy applications created by the consumer or acquired using programming languages ​​and tools supported by the provider onto cloud infrastructure. Consumers do not manage or control the underlying cloud infrastructure, including networks, servers, operating systems, or storage, but they have control over the deployed applications and the configuration of any application hosting environment.

[0065] Infrastructure as a Service (IaaS): This provides consumers with the capability to deliver processing, storage, networking, and other basic computing resources that enable them to deploy and run arbitrary software, which may include operating systems and applications. Consumers do not manage or control the underlying cloud infrastructure, but rather have control over the operating system, storage, deployed applications, and potentially limited control over selected networking components (e.g., host firewalls).

[0066] The deployment model is as follows:

[0067] Private cloud: A cloud infrastructure that operates solely for an organization. It can be managed by the organization or a third party and can exist on-site or off-site.

[0068] Community cloud: A cloud infrastructure shared by several organizations and supporting a specific community with shared concerns (e.g., tasks, security requirements, policies, and compliance considerations). It can be managed by an organization or a third party and can exist on-site or off-site.

[0069] Public cloud: Makes cloud infrastructure available to the public or large industry groups and is owned by an organization that sells cloud services.

[0070] Hybrid cloud: A cloud infrastructure is a combination of two or more clouds (private, community, or public) that remain a single entity but are bound together by standardized or proprietary technologies that enable data and applications to be ported (e.g., cloud bursting for load balancing between clouds).

[0071] Cloud computing environments are service-oriented, focusing on statelessness, loose coupling, modularity, and semantic interoperability. At the heart of cloud computing is the infrastructure comprising a network of interconnected nodes.

[0072] Now for reference Figure 5 This describes an illustrative cloud computing environment 50. As shown, the cloud computing environment 50 includes one or more cloud computing nodes 10 to which local computing devices used by cloud consumers can communicate. These local computing devices include, for example, personal digital assistants (PDAs) or cellular phones 54A, desktop computers 54B, laptop computers 54C, and / or automotive computer systems 54N. The nodes 10 can communicate with each other. They can be physically or virtually grouped (not shown) in one or more networks, such as private clouds, community clouds, public clouds, or hybrid clouds, or combinations thereof, as described above. This allows the cloud computing environment 50 to provide infrastructure, platforms, and / or software as services that cloud consumers do not need to maintain on their local computing devices. It is understood that... Figure 5 The types of computing devices 54A-N shown are intended to be illustrative only, and computing node 10 and cloud computing environment 50 can communicate with any type of computerized device via any type of network and / or network-addressable connection (e.g., using a web browser).

[0073] See now Figure 6 This demonstrates the 50 (cloud computing environment) Figure 5 This provides a set of functional abstractions. It can be understood in advance. Figure 6 The components, layers, and functions shown are intended to be illustrative only, and embodiments of the invention are not limited thereto. As described, the following layers and corresponding functions are provided:

[0074] The hardware and software layer 60 includes hardware and software components. Examples of hardware components include: a mainframe 61; a RISC (Reduced Instruction Set Computer) based server 62; a server 63; a blade server 64; a storage device 65; and network and networking components 66. In some embodiments, software components include network application server software 67 and database software 68.

[0075] The virtualization layer 70 provides an abstraction layer from which the following examples of virtual entities can be provided: virtual server 71; virtual storage 72; virtual network 73, including virtual private network; virtual application and operating system 74; and virtual client 75.

[0076] In one example, management layer 80 may provide the following functionalities: Resource Provisioning 81 provides dynamic procurement of computing resources and other resources used to perform tasks within the cloud computing environment. Metering and Pricing 82 provides cost tracking as resources are utilized within the cloud computing environment and bills or invoices for the consumption of these resources. In one example, these resources may include application software licenses. Security provides authentication for cloud consumers and tasks, as well as protection for data and other resources. User Portal 83 provides access to the cloud computing environment for consumers and system administrators. Service Level Management 84 provides cloud resource allocation and management to ensure that required service levels are met. Service Level Agreement (SLA) Planning and Fulfillment 85 provides pre-scheduling and procurement of cloud resources based on anticipated future needs according to the SLA.

[0077] Workload layer 90 provides examples of functionalities that can be leveraged in a cloud computing environment. Examples of workloads and functionalities that can be provided from this layer include: mapping and navigation 91; software development and lifecycle management 92; virtual classroom education delivery 93; data analytics and processing 94; transaction processing 95; and image classification 96.

[0078] It is understood that this disclosure can be implemented in conjunction with any other type of computing environment now known or developed in the future. For example, Figure 7 A block diagram of a processing system 700 for implementing the techniques described herein is depicted. In the example, the processing system 700 has one or more central processing units (processors) 721a, 721b, 721c, etc. (collectively or generally referred to as (a plurality of) processors 721 and / or (a plurality of) processing devices). In various aspects of this disclosure, each processor 721 may include a Reduced Instruction Set Computer (RISC) microprocessor. The processor 721 is coupled to system memory (e.g., random access memory (RAM) 724) and various other components via a system bus 733. Read-only memory (ROM) 722 is coupled to the system bus 733 and may include a basic input / output system (BIOS) that controls certain basic functions of the processing system 700.

[0079] Further depicted are input / output (I / O) adapter 727 and network adapter 726 coupled to system bus 733. I / O adapter 727 may be a Small Computer System Interface (SCSI) adapter that communicates with hard disk 723 and / or storage device 725 or any other similar component. I / O adapter 727, hard disk 723, and storage device 725 are collectively referred to herein as mass storage device 734. An operating system 740 for execution on processing system 700 may be stored in mass storage device 734. Network adapter 726 interconnects system bus 733 with external network 736, enabling processing system 700 to communicate with other such systems.

[0080] A display (e.g., a display monitor) 735 is connected to the system bus 733 via a display adapter 732, which may include a graphics adapter for improving the performance of graphics-intensive applications and video controllers. In one aspect of this disclosure, adapters 726, 727, and / or 732 may be connected to one or more I / O buses connected to the system bus 733 via an intermediate bus bridge (not shown). Suitable I / O buses for connecting peripheral devices such as hard disk controllers, network adapters, and graphics adapters typically include common protocols such as Peripheral Component Interconnect (PCI). Additional input / output devices are shown connected to the system bus 733 via a user interface adapter 728 and the display adapter 732. Input devices 729 (e.g., keyboard, microphone, touchscreen, etc.), input pointers 730 (e.g., mouse, touchpad, touchscreen, etc.), and / or speakers 731 may be interconnected to the system bus 733 via a user interface adapter 728, which may include, for example, a super I / O chip integrating multiple device adapters into a single integrated circuit.

[0081] In some aspects of this disclosure, the processing system 700 includes a graphics processing unit 737. The graphics processing unit 737 is a dedicated electronic circuit designed to manipulate and modify memory to accelerate the creation of images in a frame buffer intended for output to a display. Generally, the graphics processing unit 737 is highly efficient in manipulating computer graphics and image processing, and has a highly parallel architecture that makes it more efficient than a general-purpose CPU for algorithms that process large blocks of data in parallel.

[0082] Thus, as configured herein, the processing system 700 includes processing power in the form of a processor 721, storage capacity including system memory (e.g., RAM 724) and mass storage device 734, input devices such as a keyboard 729 and a mouse 730, and output capacity including a speaker 731 and a display 735. In some aspects of this disclosure, a portion of the system memory (e.g., RAM 724) and mass storage device 734 jointly stores an operating system 740 to coordinate the functionality of the different components shown in the processing system 700.

[0083] Various embodiments of the invention are described herein with reference to the accompanying drawings. Alternative embodiments of the invention may be devised without departing from its scope. In the following description and drawings, various connections and positional relationships (e.g., above, below, adjacent, etc.) are illustrated between elements. Unless otherwise specified, these connections and / or positional relationships may be direct or indirect, and the invention is limited in this respect by not illustrating the figures. Therefore, the connection of entities may refer to direct or indirect connections, and the positional relationship between entities may be direct or indirect positional relationships. Furthermore, the various tasks and process steps described herein may be incorporated into a more comprehensive procedure or process with additional steps or functions not described in detail herein.

[0084] One or more methods described herein can be implemented using any of the following techniques or combinations thereof known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application-specific integrated circuits (ASICs) having appropriately combined logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0085] For the sake of brevity, conventional techniques relating to the manufacture and use of the present invention may or may not be described in detail herein. Specifically, various aspects of the computing systems and specific computer programs used to implement the different technical features described herein are well known. Consequently, for the sake of brevity, many conventional implementation details are only briefly mentioned or omitted entirely herein, without providing well-known system and / or process details.

[0086] In some embodiments, various functions or actions may occur at a given location and / or in conjunction with the operation of one or more devices or systems. In some embodiments, a portion of a given function or action may be performed at a first device or location, and the remainder of the function or action may be performed at one or more additional devices or locations.

[0087] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well. It should also be understood that when the terms “comprises” and / or “comprising” are used in this specification, they specify the presence of the stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or combinations thereof.

[0088] All means or steps in the following claims, plus corresponding structures, materials, actions, and equivalents of the functional elements, are intended to include any structure, material, or action for performing the function in conjunction with other claimed elements as specifically claimed. This disclosure has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the forms disclosed. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of this disclosure. These embodiments were chosen and described in order to best explain the principles and practical application of this disclosure, and to enable others skilled in the art to understand this disclosure with respect to different embodiments having different modifications suitable for the particular intended use.

[0089] The diagrams depicted herein are illustrative. Many variations may be made to the diagrams or steps (or operations) described herein without departing from the spirit of this disclosure. For example, actions may be performed in a different order, or actions may be added, deleted, or modified. Furthermore, the term "coupled" describes a signal path between two elements and does not imply a direct connection between elements without any intermediate elements / connections. All such variations are considered part of this disclosure.

[0090] The following definitions and abbreviations will be used to interpret the claims and description. As used herein, the terms “comprising,” “including,” “comprise,” “including,” “having,” “containing,” or “containing,” or any other variation thereof, are intended to cover a non-exclusive inclusion. For example, a composition, mixture, process, method, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such composition, mixture, process, method, article, or apparatus.

[0091] Furthermore, the term "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or design described herein as "exemplary" is not necessarily to be construed as superior to or advantageous to other implementations or designs. The terms "at least one" and "one or more" should be understood to include any integer greater than or equal to one, i.e., one, two, three, four, etc. The term "multiple" should be understood to include any integer greater than or equal to two, i.e., two, three, four, five, etc. The term "connection" can include both indirect "connection" and direct "connection."

[0092] The terms “about,” “substantially,” “roughly,” and their variations are intended to include the degree of error associated with a measurement of a specific quantity based on equipment available at the time of application submission. For example, “about” could include a range of ±8%, 5%, or 2% of a given value.

[0093] This invention can be a system, method, and / or computer program product with any possible level of technical detail integration. The computer program product may include a computer-readable storage medium (or media) having computer-readable program instructions thereon for causing a processor to execute aspects of the invention.

[0094] Computer-readable storage media can be tangible means for retaining and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital universal disk (DVD), memory sticks, floppy disks, mechanical encoding devices such as punched cards, or protrusions in slots having instructions recorded thereon, and any suitable combination of the foregoing. As used herein, computer-readable storage media should not be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through fiber optic cables), or electrical signals transmitted through wires.

[0095] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a suitable computing / processing device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network), or to an external computer or external storage device. The network may include copper cables, optical fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to a computer-readable storage medium within the suitable computing / processing device.

[0096] Computer-readable program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as Smalltalk, C++, etc.) and procedural programming languages ​​(such as the "C" programming language or similar programming languages). The computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as a standalone software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)) or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) may execute computer-readable program instructions by utilizing state information from the computer-readable program instructions to personalize the electronic circuitry in order to perform aspects of this invention.

[0097] The present invention will now be described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0098] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / actions specified in the boxes or blocks of a flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner, such that the computer-readable storage medium storing the instructions includes an article of manufacture containing instructions that implement aspects of the functions / actions specified in the boxes or blocks of a flowchart and / or block diagram.

[0099] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other device to produce computer-implemented processing, such that the instructions executed on the computer, other programmable apparatus, or other device perform the functions / actions specified in the boxes or blocks of a flowchart and / or block diagram.

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of instructions, including one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than indicated in the figures. For example, depending on the functions involved, two consecutively shown blocks may actually be executed substantially simultaneously, or these blocks may sometimes be executed in reverse order. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action or executes a combination of dedicated hardware and computer instructions.

[0101] Various embodiments of the invention have been described for illustrative purposes, but are not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein has been chosen to best explain the principles of the embodiments, their practical application, or technical improvements over those found in the market, or to enable those skilled in the art to understand the embodiments described herein.

Claims

1. A computer-implemented method for detecting well sites, comprising: The processor uses a first machine learning model, based at least in part on a first dataset, to detect the identity and composition of gas emissions at a first location to identify a first well site at the first location, the first dataset including spectral data describing gas emissions from the first location; The processor detects environmental events within a threshold distance of the well site; The processor determines the probability of damage to the first well site caused by the environmental event; as well as The suitable location of a second well site at the second location is predicted, at least in part, based on the similarity of the terrain between the first location and the second location without a well site and the probability of damage caused by environmental events at the second location.

2. The computer-implemented method according to claim 1, wherein, The environmental event referred to is a fire, landslide, or flood.

3. The computer-implemented method of claim 1 further includes using a second machine learning model to extract features from the first dataset to determine the terrain at the location.

4. The computer-implemented method of claim 1 further includes encoding the data at least in part based on the terrain to delineate the boundaries of potential well sites.

5. The computer-implemented method according to claim 4, wherein, The first machine learning model determines whether a bounded potential well site is a source of the gas emissions.

6. The computer-implemented method of claim 1 further includes determining the identity, composition, and volume of the gas emission, and comparing the emission with regulation requirements.

7. A system for detecting well sites, comprising: Memory having computer-readable instructions; as well as One or more processors are configured to execute the computer-readable instructions, the computer-readable instructions controlling the one or more processors to perform operations, the operations including: The first machine learning model is used to detect the identity and composition of gas emissions at a first location, based at least in part on a first dataset, to identify a first well site at the first location, the first dataset including spectral data describing gas emissions from the first location; Detect environmental events within a threshold distance of the well site; Determine the probability of damage to the first well site caused by the environmental event; and The suitable location of a second well site at the second location is predicted, at least in part, based on the similarity of the terrain between the first location and the second location without a well site and the probability of damage caused by environmental events at the second location.

8. The system according to claim 7, wherein, The environmental event referred to is a fire, landslide, or flood.

9. The system of claim 7, further comprising using a second machine learning model to extract features from the first dataset to determine the terrain at the location.

10. The system of claim 7, further comprising encoding the data at least in part based on the terrain to delineate the boundaries of potential well sites.

11. The system according to claim 10, wherein, The first machine learning model determines whether a bounded potential well site is a source of the gas emissions.

12. The system of claim 7, further comprising determining the identity, composition and volume of the gas emission, and comparing the emission with regulation requirements.

13. A computer program product comprising a computer-readable storage medium having program instructions embodied therein, the program instructions being executable by a processor to cause the processor to perform operations, the operations including: The first machine learning model is used to detect the identity and composition of gas emissions at a first location, based at least in part on a first dataset, to identify a first well site at the first location, the first dataset including spectral data describing gas emissions from the first location; Detect environmental events within a threshold distance of the well site; Determine the probability of damage to the first well site caused by the environmental event; as well as The suitable location of a second well site at the second location is predicted, at least in part, based on the similarity of the terrain between the first location and the second location without a well site and the probability of damage caused by environmental events at the second location.

14. The computer program product according to claim 13, wherein, The environmental event referred to is a fire or a flood.

15. The computer program product of claim 13, wherein the operation further comprises using a second machine learning model to extract features from the first dataset to determine the terrain of the location.

16. The computer program product of claim 13, further comprising encoding the data at least in part based on the terrain to delineate the boundaries of potential well sites.

17. The computer program product according to claim 16, wherein, The first machine learning model determines whether a bounded potential well site is a source of the gas emissions.

Images