Firing point spreading prediction method and device and computer program product

Abstract

The invention discloses a fire point spreading prediction method and device and a computer program product, and the method comprises the steps: determining a grid with a latest fire point in a grid set, and obtaining a first grid, the grid set comprising a plurality of grids obtained by dividing an area comprising the fire point; under the condition that the grids which are adjacent to the first grid and have no fire point in the grid set are a group of grids, determining predicted spreading time of the fire point spreading from the first grid to each grid in the group of grids, and obtaining a group of predicted spreading time; based on the set of predicted spread times, a grid in the set of grids where the fire point occurs earliest after the fire point occurs in the first grid is predicted. Through the method and the device, the problem of low accuracy of fire spreading prediction in related technologies is solved, and the effect of improving the accuracy of fire spreading prediction is achieved.

Description

Technical Field

[0001] This application relates to the field of computers, and more specifically, to a method, apparatus, and computer program product for predicting the spread of a fire ignition point. Background Technology

[0002] As a common disaster, fire has a complex and varied spread mechanism, which is affected by a variety of factors such as meteorological conditions, topographic features and vegetation distribution.

[0003] Currently, fire spread prediction is mainly divided into three categories: physical models, empirical models, and data-driven models. However, all three types of models rely on large-scale, high-quality historical fire data for fire spread prediction and analysis. They are difficult to effectively integrate key information from the fire scene, such as vegetation type, fuel load, and historical fire point distribution, thus limiting the accuracy, robustness, and applicability of the prediction models in complex and variable environments.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This application provides a method, apparatus, and computer program product for predicting the spread of ignition points, in order to at least solve the technical problem of low accuracy in predicting the spread of ignition points in related technologies.

[0006] According to one aspect of the embodiments of this application, a method for predicting the spread of a fire point is provided, comprising: determining the grid in a grid set where the latest fire point appears to be obtained, to obtain a first grid, wherein the grid set includes multiple grids obtained by dividing the area containing the fire point; in the case that the grids in the grid set that are adjacent to the first grid and have not yet produced a fire point are a group of grids, determining the estimated spread time of the fire point from the first grid to each grid in the group of grids to obtain a set of estimated spread times; and based on the set of estimated spread times, predicting the grid in the group of grids where the earliest fire point appears after the fire point appears in the first grid.

[0007] In an exemplary embodiment, when the grids adjacent to the first grid in the grid set that have not yet shown an ignition point constitute a group of grids, determining the estimated spread time of the ignition point from the first grid to each grid in the group of grids, and obtaining a set of estimated spread times, includes: performing the following operations on each grid in the group of grids respectively, wherein each grid in the group of grids is the current grid when performing the following operations: determining a set of spread parameter values ​​for the current grid; and determining the estimated spread time of the ignition point from the first grid to the current grid based on the set of spread parameter values.

[0008] In one exemplary embodiment, determining the estimated spread time of the fire from the ignition point to the current grid based on a set of spread parameter values ​​includes: determining the distance between the center point of the first grid and the center point of the current grid; determining the spread velocity of the fire from the ignition point to the current grid based on a set of spread parameter values; and determining the estimated spread time of the fire from the ignition point to the current grid based on the distance and the spread velocity.

[0009] In an exemplary embodiment, determining the spread rate of an ignition point from a first grid to a current grid based on a set of spread parameter values ​​includes: determining a first spread rate of an ignition point from the first grid to the current grid based on a first portion of the spread parameter values ​​in the set of spread parameter values, wherein the first portion of the spread parameter values ​​is used to characterize the physical properties of the fuel in the area represented by the current grid; determining a second spread rate of an ignition point from the first grid to the current grid based on a second portion of the spread parameter values ​​in the set of spread parameter values, wherein the second portion of the spread parameter values ​​is used to characterize the distribution characteristics of the fuel in the area containing the ignition point; and determining the spread rate as a weighted sum of the first spread rate and the second spread rate.

[0010] In an exemplary embodiment, determining a first spread rate from the ignition point to the current grid based on a first portion of spread parameter values ​​from a set of spread parameter values ​​includes: determining a terrain factor and a wind speed factor for the current grid, wherein the terrain factor is used to represent the degree of influence of the terrain in the area represented by the current grid on the spread rate of the ignition point, and the wind speed factor is used to represent the degree of influence of the wind speed in the area represented by the current grid on the spread rate of the ignition point; and determining the first spread rate based on the first portion of spread parameter values, the terrain factor, and the wind speed factor.

[0011] In an exemplary embodiment, determining a first spread rate based on a first set of spread parameter values, a terrain factor, and a wind speed factor includes: determining the sum of a preset value, the terrain factor, and the wind speed factor as a first parameter value; determining a second parameter value by multiplying the reaction intensity of the fuel in the area represented by the current grid, the flux coefficient of the ignition point during the spread process, and the first parameter value, wherein the first set of spread parameter values ​​includes the reaction intensity and the flux coefficient, the reaction intensity being used to represent the amount of energy released by the fuel during combustion per unit time and per unit area, and the flux coefficient being used to represent the amount of energy transferred by the ignition point during spread per unit time and per unit area; determining a third parameter value by multiplying the volume density of the fuel in the area represented by the current grid, the effective heating number of the current grid, and the pre-combustion heat of the current grid, wherein the first set of spread parameter values ​​also includes the volume density, the effective heating number, and the pre-combustion heat, the effective heating number being used to represent the ratio of the energy used for heating during combustion to the energy used to maintain the flame in the area represented by the current grid, and the pre-combustion heat being used to represent the minimum energy required for the ignition point to appear in the current grid; and determining the first spread rate based on the first parameter value, the second parameter value, and the third parameter value.

[0012] In one exemplary embodiment, determining a first spread rate based on a first parameter value, a second parameter value, and a third parameter value includes: determining the product of the first parameter value and the second parameter value as a first product; and determining the ratio of the first product to the third parameter value as the first spread rate.

[0013] In an exemplary embodiment, determining a second spread rate from the ignition point to the current grid based on a second portion of spread parameter values ​​from a set of spread parameter values ​​includes: obtaining an initial spread rate from the ignition point to the current grid; determining a fuel type correction coefficient, a wind speed correction coefficient, and a terrain correction coefficient for the fuel in the area represented by the current grid, wherein the second portion of the spread parameter values ​​includes the fuel type correction coefficient; and determining the product of the initial spread rate, the fuel type correction coefficient, the wind speed correction coefficient, and the terrain correction coefficient as the second spread rate.

[0014] In one exemplary embodiment, determining the estimated spread time from the ignition point to the current grid based on distance and spread speed includes: obtaining the moment when the ignition point appears in the first grid to obtain a first time; determining the ratio of distance to spread speed as a time interval; and determining the sum of the first time and the time interval as the estimated spread time from the ignition point to the current grid.

[0015] In one exemplary embodiment, predicting the earliest ignition point after the first ignition point in a set of grids based on a set of expected spread times includes: determining the minimum expected spread time in the set of expected spread times; and determining the grid in the set of grids corresponding to the minimum expected spread time as the earliest ignition point after the first ignition point in the set of grids.

[0016] In one exemplary embodiment, the method further includes: if there is a third grid in the grid set whose expected spread time is earlier than the minimum expected spread time, determining the third grid as the grid in the grid set that has the earliest ignition point after the first grid.

[0017] In an exemplary embodiment, before determining the estimated spread time from the ignition point to each grid in the set of grids and obtaining a set of estimated spread times, the method further includes: obtaining grids in the set of grids that are adjacent to the first grid and have not yet had an ignition point, thus obtaining a plurality of adjacent grids; determining the plurality of adjacent grids as a set of grids, or determining the grids in the plurality of adjacent grids that do not have firebreaks as a set of grids.

[0018] In one exemplary embodiment, determining the grid where the latest ignition point appears in the grid set to obtain a first grid includes: determining the grids where the ignition point has appeared in the grid set to obtain multiple candidate grids; determining the time when the ignition point appears in each of the multiple candidate grids to obtain multiple ignition times corresponding one-to-one with the multiple candidate grids; determining the latest ignition time among the multiple ignition times; and determining the grid corresponding to the latest ignition time among the multiple candidate grids as the first grid.

[0019] In an exemplary embodiment, the method includes: repeatedly performing a prediction operation until a preset condition is met, wherein the prediction operation includes: determining the grid where the latest ignition point appears in a grid set to obtain a first grid, wherein the grid set includes multiple grids obtained by dividing the area containing the ignition point; if the grids adjacent to the first grid in the grid set that have not yet ignited a point form a group of grids, determining the estimated spread time for the ignition point to spread from the first grid to each grid in the group of grids to obtain a group of estimated spread times; based on the group of estimated spread times, predicting the grid where the earliest ignition point appears after the first grid appears in the group of grids, and using the predicted grid as the grid where the latest ignition point appears; and determining the spread path of the ignition point based on the predicted grids.

[0020] In one exemplary embodiment, the preset conditions include at least one of the following: the number of times the prediction operation is executed is greater than or equal to a preset number; the total execution time of repeatedly executing the prediction operation is greater than or equal to a preset duration; the total number of predicted grids is greater than or equal to a preset number; and the total area of ​​predicted grids is greater than or equal to a preset area.

[0021] According to another aspect of the embodiments of this application, a fire spread prediction device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following operations: determining the grid in a grid set where the latest fire point appears to be found, obtaining a first grid, wherein the grid set includes multiple grids obtained by dividing the area containing the fire point; when the grids in the grid set that are adjacent to the first grid and have not yet found a fire point form a group of grids, determining the estimated spread time of the fire point from the first grid to each grid in the group of grids, obtaining a set of estimated spread times; and based on the set of estimated spread times, predicting the grid in the group of grids where the earliest fire point appears after the first grid point appears.

[0022] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed by a processor.

[0023] According to another aspect of the embodiments of this application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform the steps in any of the method embodiments described above.

[0024] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to perform the steps in any of the above method embodiments through the computer program.

[0025] This application divides the area containing the ignition point into a grid set, and identifies the first grid in the grid set where the ignition point has recently appeared. Then, it finds a group of grids around the first grid where no ignition point has appeared yet, and calculates the estimated spread time from the ignition point from the first grid to each grid in the group of grids, obtaining a set of estimated spread times. Based on the set of estimated spread times, it predicts the grid in the group of grids where the ignition point will appear earliest after the ignition point appears in the first grid.

[0026] By considering the natural spread of fire, determining the grid where the latest ignition point is located, and calculating the estimated time for its spread to neighboring unburned grids, this method, through gridding and a step-by-step spread prediction approach, achieves a refined simulation of fire spread paths and speeds. This effectively overcomes the high dependence on large-scale, high-quality historical fire annotation data, significantly improving the accuracy and practicality of predictions. Particularly in forest fire prevention decision support, it provides a more scientific and quantitative basis, enhancing the model's generalization ability and its capacity to cope with complex and changing environments. Therefore, it can solve the problem of low accuracy in ignition point spread prediction in related technologies, achieving the effect of improving the accuracy of ignition point spread prediction. Attached Figure Description

[0027] Figure 1 This is a schematic diagram illustrating an application scenario of the fire ignition point propagation prediction method according to an embodiment of this application;

[0028] Figure 2 This is a flowchart illustrating a method for predicting the spread of ignition points according to an embodiment of this application.

[0029] Figure 3 This is a schematic diagram of remote sensing image gridding according to an embodiment of this application;

[0030] Figure 4 This is a schematic diagram of the spread of the ignition point according to an embodiment of this application. Figure 1 ;

[0031] Figure 5 This is a schematic diagram of the spread of the ignition point according to an embodiment of this application. Figure 2 ;

[0032] Figure 6 This is a propagation prediction process based on embodiments of this application. Figure 1 ;

[0033] Figure 7 This is a propagation prediction process based on embodiments of this application. Figure 2 ;

[0034] Figure 8 This is a schematic diagram of the spread of the ignition point according to an embodiment of this application. Figure 3 ;

[0035] Figure 9 This is a schematic diagram of the spread of the ignition point according to an embodiment of this application. Figure 4 ;

[0036] Figure 10 This is a schematic diagram of the spread of the ignition point according to an embodiment of this application. Figure 5 ;

[0037] Figure 11This is a structural block diagram of a fire point spread prediction device according to an embodiment of this application. Detailed Implementation

[0038] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0039] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0040] According to one aspect of the embodiments of this application, a method for predicting the spread of ignition points is provided. Optionally, in this embodiment, the above-described method for predicting the spread of ignition points may be applied, but is not limited to, to applications such as... Figure 1 The application scenario is illustrated in the diagram. This application scenario may include satellite 102 and terminal 104.

[0041] In this disclosure, satellite 102 is an entity used for collecting or transmitting data, and there can be multiple satellites. This disclosure does not limit the specific technology or equipment form used in the satellites.

[0042] In this embodiment of the disclosure, terminal 104 refers to a processing device within the satellite coverage beam range for communicating with a satellite. A database can be set up on or independently of terminal 104 to provide data storage services for terminal 104. For example, the terminal can be a car with satellite communication capabilities, a smart car, a mobile phone, a wearable device, a tablet computer, a server, etc. This disclosure does not limit the specific technology or device form used in the terminal. It should be noted that... Figure 1 The example uses two terminal devices 104.

[0043] It is understood that the application scenarios described in the embodiments of this disclosure are for the purpose of more clearly illustrating the technical solutions of the embodiments of this disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this disclosure are also applicable to similar technical problems.

[0044] Taking the prediction method for the spread of fire ignition points in this embodiment, executed by terminal 104, as an example, Figure 2 This is a flowchart illustrating a method for predicting the spread of ignition points according to an embodiment of this application, as shown below. Figure 2 As shown, the process of this method may include the following steps:

[0045] Step S202: Determine the grid where the latest ignition point appears in the grid set to obtain the first grid. The grid set includes multiple grids obtained by dividing the area containing the ignition point.

[0046] The aforementioned grid set can be a collection of multiple grids (or grid cells) obtained by dividing geospatial data (such as remote sensing images, elevation, vegetation cover, etc.) according to a unified resolution and extent standard. Each grid can contain specific information about the area it represents, such as elevation and vegetation cover type. Dividing data into grids facilitates data processing, analysis, and visualization of the collected data.

[0047] Example, Figure 3 This is a schematic diagram of remote sensing image gridding according to an embodiment of this application, such as... Figure 3 As shown, taking the occurrence of a fire in a forest as an example, after acquiring remote sensing images of a specific area (such as a forest), the acquired remote sensing images are cropped according to the actual location of the fire in the forest, so that the cropped remote sensing image contains a suitable area (i.e., the area containing the fire). Figure 3 (The shaded area represents the region where the fire started.) Then, the region is divided into multiple grids according to a unified resolution and range standard, and each grid is numbered to obtain a grid set, thus realizing the gridding of the remote sensing image. In the grid set, each grid represents a part of the forest, and grid 33 represents the area where the fire started.

[0048] The first grid mentioned above can be the grid where the fire point most recently appeared in the grid set, that is, the most recently appeared fire point when the fire spread prediction is performed. For example, if the current fire spread prediction is performed at 12:00, then the fire point that last appeared before 12:00 (such as appearing at 11:59) is defined as the most recently appeared fire point, and the grid where the most recently appeared fire point is located is the first grid.

[0049] In this embodiment of the application, when predicting the spread of the ignition point, the collected data are first gridded to form a grid set. Each grid in the grid set contains specific information about the area represented by that grid. Then, based on the specific information contained in each grid, the first grid where the latest ignition point appears is determined in the grid set.

[0050] As an optional implementation, determining the grid where the latest ignition point appears in the grid set to obtain the first grid includes: determining the grids where the ignition point has appeared in the grid set to obtain multiple candidate grids; determining the time when the ignition point appears in each of the multiple candidate grids to obtain multiple ignition times that correspond one-to-one with the multiple candidate grids; determining the latest ignition time among the multiple ignition times; and determining the grid corresponding to the latest ignition time among the multiple candidate grids as the first grid.

[0051] Step S204: In the case that the grids adjacent to the first grid in the grid set and for which no ignition point has yet appeared are a group of grids, determine the estimated spread time of the ignition point from the first grid to each grid in the group of grids, and obtain a set of estimated spread times.

[0052] The aforementioned set of grids can be a collection of grids that have not yet shown an ignition point among the grids adjacent to the first grid. For example, after the collected data is gridded, each grid will contain the combustion state of the area represented by that grid (i.e., whether an ignition point has appeared). If the grid has not yet shown an ignition point (e.g., unburned state) or the grid has shown an ignition point (e.g., burning state or burnt-out state), then, based on the combustion state of each grid, the grids that have not yet shown an ignition point among the 8 grids surrounding the first grid can be determined in the grid set, thus obtaining a set of grids.

[0053] Figure 4 This is a schematic diagram of the spread of the ignition point according to an embodiment of this application. Figure 1 ,like Figure 4 As shown, when grid 33 is the first grid, the grids that have not yet shown an ignition point among the adjacent grids of the first grid (including grids 22, 23, 24, 32, 34, 42, 43, and 44) ​​are identified as a group of grids. At this time, a group of grids can be grids 22, 23, 24, 32, 34, 42, 43, and 44.

[0054] The predicted spread time can be the time when the ignition point appears in the area represented by the grid (i.e., the grid). This time can be a specific moment, such as 11:00, 11:05, 11:05:35, etc., without any specific restrictions.

[0055] In this embodiment of the application, since the area around the ignition point is usually the most likely to be ignited and develop into an ignition point, after determining the first grid, a group of grids adjacent to the first grid that have not yet developed into an ignition point are determined as candidate grids in the grid set, and the estimated spread time of the ignition point from the first grid to each grid in the group of grids is calculated, so as to determine the spread trend of the ignition point based on the estimated spread time.

[0056] Step S206: Based on a set of expected propagation times, predict the grid in a set of grids that will be the earliest to ignite after the first grid.

[0057] Through the above steps, the area containing the ignition point is divided into a grid set, and the first grid in which the ignition point appears is determined. Then, a group of grids around the first grid that has not yet appeared are found. At the same time, the estimated spread time of the ignition point from the first grid to each grid in the group is calculated to obtain a set of estimated spread times. Based on the set of estimated spread times, the grid in the group that will appear earliest after the ignition point appears in the first grid is predicted.

[0058] By considering the natural spread of fire, determining the grid where the latest ignition point is located, and calculating the estimated time for its spread to neighboring unburned grids, this method, through gridding and a step-by-step spread prediction approach, achieves a refined simulation of fire spread paths and speeds. This effectively overcomes the high dependence on large-scale, high-quality historical fire annotation data, significantly improving the accuracy and practicality of predictions. Particularly in forest fire prevention decision support, it provides a more scientific and quantitative basis, enhancing the model's generalization ability and its capacity to cope with complex and changing environments. It also solves the problem of low accuracy in ignition point spread prediction in related technologies, improving the accuracy of ignition point spread prediction.

[0059] The entities that perform the above steps can be servers, terminals, etc., but are not limited to these.

[0060] Example 1:

[0061] In this application, the spread of a fire can be predicted only once to predict the area where the next fire will occur. The specific implementation method is shown in the following steps. It should be noted that the following description uses a forest fire as an example to illustrate the detailed implementation steps. In practical applications, it can be applied to any fire prediction scenario, and no specific limitations are made here.

[0062] As an optional implementation, when the grids adjacent to the first grid in the grid set that have not yet shown an ignition point are considered as a group of grids, the estimated spread time of the ignition point from the first grid to each grid in the group of grids is determined to obtain a set of estimated spread times. This includes: performing the following operations on each grid in the group of grids respectively to obtain a set of estimated spread times, wherein each grid in the group of grids is the current grid when performing the following operations: determining a set of spread parameter values ​​for the current grid; and determining the estimated spread time of the ignition point from the first grid to the current grid based on the set of spread parameter values.

[0063] The current grid mentioned above can be any grid in a set of grids that is being analyzed and whose expected spread time is being calculated.

[0064] The aforementioned spread parameter values ​​can be numerical values ​​of parameters that influence the spread trend of the ignition point (such as speed and direction). These parameters include, but are not limited to, wind speed, wind direction, humidity, terrain slope, physical properties of fuel, and fuel distribution characteristics. They are used to calculate the spread rate and estimated spread time of the ignition point. The physical properties of the fuel typically refer to the material properties constituting the fuel, such as fuel type, fuel humidity, fuel bulk density, and fuel calorific value. The fuel distribution characteristics typically refer to the spatial layout of the fuel, such as the continuity of fuel distribution and fuel distribution patterns (such as uniform distribution and patchy distribution), to reflect the type and quantity of fuel in different areas. In this embodiment, the aforementioned fuel can refer to combustible materials contained in the current grid, such as dry grass, trees, and fallen leaves. The specific types of combustible materials contained in the current grid can be determined by acquiring remote sensing images.

[0065] For example, when predicting the spread of a fire, the land cover (such as grassland, woodland, water bodies, and bare land) within the area containing the fire point can be obtained based on the acquired remote sensing images. The mapping relationship between land cover type and fuel characteristics within each grid in the grid set is then used to determine the fuel characteristics (i.e., spread parameter values) within each grid area, thus achieving a gridded representation of the land cover. Simultaneously, based on the acquired remote sensing images, digital elevation model (DEM) processing is used to obtain digital elevation data for the areas represented by each grid in the grid set, thereby determining the terrain height information for each grid. Furthermore, the acquired meteorological data (such as wind speed, wind direction, temperature, and humidity) is gridded to determine the meteorological information for each grid.

[0066] In this embodiment of the application, the estimated spread time from the ignition point to each grid in the group of grids is calculated. Specifically, a set of spread parameter values ​​for the current grid is determined, including but not limited to wind speed, wind direction, terrain height, fuel type and air humidity. Then, based on a comprehensive analysis of the set of spread parameter values, the estimated spread time from the ignition point to the current grid is determined.

[0067] By following the steps above, the estimated spread time from the ignition point to the adjacent grid can be accurately calculated. This helps to capture subtle changes in the fire spread process, reflects the possibility and speed of the fire spreading to the surrounding unaffected areas, and provides timely and accurate data support for forest fire prevention decisions.

[0068] As an optional implementation, the estimated spread time of the fire from the ignition point to the current grid is determined based on a set of spread parameter values, including: determining the distance between the center point of the first grid and the center point of the current grid; determining the spread speed of the fire from the ignition point to the current grid based on a set of spread parameter values; and determining the estimated spread time of the fire from the ignition point to the current grid based on the distance and the spread speed.

[0069] The aforementioned distance can be the distance between the center points of two grids, used to represent the regional distance between the areas represented by the two grids, that is, the spread distance from the ignition point from one grid to another.

[0070] The aforementioned spread rate can be a physical quantity describing how quickly a fire spreads from its ignition point. This physical quantity is affected by a variety of factors, such as wind speed, terrain slope, fuel type, and fuel load.

[0071] In this embodiment of the application, the straight-line distance (i.e., distance) between the center point of the first grid and the center point of the current grid is first determined. Then, the spread rate of the fire from the first grid to the current grid is determined based on a set of spread parameters. Finally, the expected spread time of the fire from the first grid to the current grid is determined based on the spread rate and the distance.

[0072] For example, based on distance and spread rate, the estimated spread time from the ignition point to the current grid is determined, including: obtaining the moment when the ignition point appears in the first grid to obtain the first time; determining the ratio of distance to spread rate as the time interval; and determining the sum of the first time and the time interval as the estimated spread time from the ignition point to the current grid.

[0073] By combining the calculated distance and spread rate through the above operations, the estimated spread time from the ignition point to the current grid is obtained, ensuring high accuracy and reliability in predicting the fire spread process. This method, based on a combination of physical laws and empirical formulas, enables precise modeling of the spread time series, providing timely and reliable information support for fire prevention decisions and playing a crucial role in fire early warning, resource allocation, and firebreak planning. Furthermore, by dynamically adjusting the calculation parameters of the spread rate based on real-time monitoring data, the model's adaptability to complex and changing environments is further enhanced, ensuring the accuracy and robustness of the prediction results. This allows the model to flexibly respond to different scenarios and optimize the accuracy of the spread time prediction.

[0074] As an optional implementation, the propagation speed of the ignition point spreading from the first grid to the current grid is determined based on a set of propagation parameter values, including: determining a first propagation speed of the ignition point spreading from the first grid to the current grid based on a first portion of the propagation parameter values ​​in the set of propagation parameter values, wherein the first portion of the propagation parameter values ​​is used to characterize the physical properties of the fuel in the area represented by the current grid; determining a second propagation speed of the ignition point spreading from the first grid to the current grid based on a second portion of the propagation parameter values ​​in the set of propagation parameter values, wherein the second portion of the propagation parameter values ​​is used to characterize the distribution characteristics of the fuel in the area containing the ignition point; and determining the propagation speed as a weighted sum of the first propagation speed and the second propagation speed.

[0075] The first part of the spread parameter values ​​mentioned above can be parameter values ​​used to characterize the physical properties of the fuel in the area represented by the current grid, that is, the parameter values ​​of the physical properties of the fuel in the area represented by the grid currently being analyzed. It mainly focuses on the physical properties of the fuel and energy transfer during combustion. The physical properties of the fuel typically refer to the material properties that constitute the fuel, such as fuel type, fuel moisture content, fuel bulk density, and fuel calorific value. For example, when determining the fuel characteristics (i.e., spread parameter values) in the area represented by each grid in the grid set based on the mapping relationship between land cover type and fuel characteristics, the gridded land cover can be transformed into a Rothermel fuel distribution grid. The first part of the spread parameter values ​​can then be obtained based on the Rothermel fuel distribution grid. The Rothermel fuel distribution grid is a gridded representation based on the Rothermel model, which divides forest ground fuel into multiple standard types (such as surface fuel, subsurface fuel, etc.), each with specific physical parameters (such as calorific value, moisture content, bulk density, etc.) used to calculate flame propagation speed and flame energy.

[0076] The second part of the spread parameter values ​​mentioned above can be parameter values ​​used to characterize the distribution characteristics of fuel within the area containing the ignition point, that is, parameter values ​​of the distribution characteristics of fuel within the entire area containing the ignition point. It mainly focuses on the impact of fuel distribution and combustible material type on fire spread. Fuel distribution characteristics typically refer to the spatial layout of fuel, such as the continuity of fuel distribution and fuel distribution patterns (e.g., uniform distribution, patchy distribution), to reflect the type and quantity of fuel in different areas. For example, when determining the fuel characteristics (i.e., spread parameter values) within the area represented by each grid in the grid set based on the mapping relationship between land cover type and fuel characteristics, the gridded land cover can be transformed into the Wang Zhengfei fuel distribution grid. The second part of the spread parameter values ​​can then be obtained based on the Wang Zhengfei fuel distribution grid, which classifies and quantifies the fuel on the forest floor (e.g., leaves, branches, herbaceous plants, etc.) to reflect the type, quantity, and distribution characteristics of fuel in different areas.

[0077] In this embodiment, a set of spread parameter values ​​is analyzed and divided into a first part and a second part. A first spread rate is determined based on the first part and a second spread rate is determined based on the second part. The first spread rate is determined based on the physical characteristics of the fuel within the current grid (such as fuel type, moisture content, and bulk density), reflecting the influence of the fuel itself on the spread rate of the ignition point. The second spread rate focuses on the distribution characteristics of the fuel in the area where the ignition point is located, considering environmental factors such as terrain slope, and assessing the effect of external conditions on the spread rate of the ignition point. Finally, the first and second spread rates are combined by a weighted sum to obtain the final spread rate. Specifically, the spread rate can be determined using the following formula:

[0078]

[0079] In the formula, It's the speed of spread. It is the fastest rate of spread. It is the second fastest rate of spread. , These are weighting coefficients. In the embodiments of this application, It can be a preset weighting coefficient, with a value range of [0,1].

[0080] Through the above operations, a two-tiered assessment of the spread rate based on physical characteristics and environmental distribution characteristics is conducted. This ensures that the model comprehensively considers both internal and external factors of fire spread, enabling a more refined simulation of the fire spread process and improving the accuracy and robustness of predictions. Furthermore, the selection and weighting of spread parameter values ​​can be adjusted based on actual conditions and needs to adapt to the requirements of fire spread prediction in different regions or specific environments, thus enhancing the model's flexibility and generalization ability.

[0081] As an optional implementation, a first spread rate is determined based on a first portion of the spread parameter values ​​from a set of spread parameter values, which includes: determining the terrain factor and wind speed factor of the current grid, wherein the terrain factor is used to represent the degree of influence of the terrain in the area represented by the current grid on the spread rate of the fire point, and the wind speed factor is used to represent the degree of influence of the wind speed in the area represented by the current grid on the spread rate of the fire point; and the first spread rate is determined based on the first portion of the spread parameter values, the terrain factor, and the wind speed factor.

[0082] The aforementioned terrain factors can represent the degree to which terrain features influence the spread rate of a fire from its ignition point, such as the influence of slope or altitude differences. Generally, the greater the slope or altitude difference, the higher the value of the terrain factor, indicating that the terrain is more conducive to fire spread. The terrain factor can be determined using the following formula:

[0083]

[0084] In the formula, It is a topographic factor. It is the fuel packing ratio within the area represented by the current grid, where, , It can represent the dry particle density of fuel, and is a preset fixed value. It can represent the dry bulk density of fuel. The drying fuel load can be represented by analyzing the collected remote sensing data. This can represent the average depth of fuel within the area represented by the current grid. In the embodiments of the application, the depth of fuel can be determined by analyzing the acquired remote sensing images. The slope is determined by the ratio of the elevation difference to the distance. The elevation difference can be the difference in elevation between the center point of the first grid and the center point of the current grid, and the distance can be the straight-line distance between the center points of the first and second grids. It should be noted that the specific parameters in the above formula are only a set of preferred values ​​and can be adjusted according to actual conditions.

[0085] The wind speed factor described above represents the degree to which wind speed affects the spread rate of a fire. The faster the wind speed, the larger the wind speed factor, and the faster the fire spreads. Specifically, the wind speed factor can be determined using the following formula:

[0086]

[0087] In the formula, It is the wind speed factor. It is the first correction factor, preferably, and can take values ​​of [value missing]. ,in, It can represent the ratio of fuel surface area to volume. The specific parameters can be adjusted according to the actual situation. This refers to the flame height and wind speed, which is a preset fixed value. The specific setting can be adjusted according to the situation. It is the second correction factor, preferably, and can take the value of ,in, It can represent the ratio of fuel surface area to volume. The specific parameters can be adjusted according to the actual situation. It is the fuel packing ratio within the area represented by the current grid. It represents the optimal fuel packing ratio for the region represented by the current grid. This is the third correction factor. It should be noted that the first, second, and third correction factors are all calculated based on the fuel particle size.

[0088] As an optional implementation, a first spread rate is determined based on a first set of spread parameter values, a terrain factor, and a wind speed factor, including: determining the sum of preset values, the terrain factor, and the wind speed factor as a first parameter value; determining a second parameter value by multiplying the reaction intensity of the fuel in the area represented by the current grid, the flux coefficient of the ignition point during the spread process, and the first parameter value, wherein the first set of spread parameter values ​​includes the reaction intensity and the flux coefficient, the reaction intensity being used to represent the amount of energy released by the fuel during combustion per unit time and per unit area, and the flux coefficient being used to represent the amount of energy transferred by the ignition point during spread per unit time and per unit area; determining a third parameter value by multiplying the volume density of the fuel in the area represented by the current grid, the effective heating number of the current grid, and the pre-combustion heat of the current grid, wherein the first set of spread parameter values ​​also includes the volume density, the effective heating number, and the pre-combustion heat, the effective heating number being used to represent the ratio of the energy used for heating during combustion to the energy used to maintain the flame in the area represented by the current grid, and the pre-combustion heat being used to represent the minimum energy required for the ignition point to appear in the current grid; and determining the first spread rate based on the first parameter value, the second parameter value, and the third parameter value.

[0089] The aforementioned reaction intensity can be the amount of energy released by fuel during combustion within the area represented by the current grid (i.e., the ability to release energy), reflecting the rate at which fuel is converted into smoke, ash, and gaseous products, and the efficiency of heat release in this process, typically expressed in watts per square meter (W / m²). 2 The reaction intensity is indicated by (). This reaction intensity is influenced by fuel type, dryness, structure, and environmental conditions. For example, the reaction intensity of the fuel within the area represented by the current grid can be determined using the following formula:

[0090]

[0091] In the formula, It represents the reaction intensity of the fuel within the area represented by the current grid. It represents the reaction rate of fuel within the region represented by the current grid. It is the net fuel load of the fuel within the area represented by the current grid. It represents the calorific value of the fuel within the area represented by the current grid. It is the moisture damping coefficient of the fuel within the area represented by the current grid. It is the mineral damping coefficient of the fuel within the area represented by the current grid.

[0092] For example, the reaction rate can be the speed at which fuel burns under specific conditions, used to measure how quickly fuel transforms from a solid (or liquid) state into gaseous products (such as carbon dioxide, water vapor, etc.). In the embodiments of this application, the fuel reaction rate describes the rate at which natural fuels such as wood, fallen leaves, and grass undergo an oxidation reaction to produce combustion products under the action of an ignition point. The reaction rate can be determined by the following formula:

[0093]

[0094] In the formula, It is the maximum reaction rate of fuel within the region represented by the current grid. Preferably, it can be set to a value of [value missing]. ,in, It is the ratio of the surface area to the volume of fuel within the region represented by the current grid. The specific parameters can be adjusted according to the actual situation. It is the fuel packing ratio within the area represented by the current grid. It is the fourth correction factor, which is preferred and can take the value of [value missing]. ,in, It is the ratio of the surface area to the volume of fuel within the region represented by the current grid. The specific parameters can be adjusted according to the actual situation. It is the optimal packing ratio for fuel within the area represented by the current grid. Preferably, it can be set to a value of [value missing]. ,in, It is the ratio of the surface area to the volume of fuel within the region represented by the current grid. The specific parameters can be adjusted according to the actual situation.

[0095] For example, net fuel load can be the combustible mass of fuel (such as dead wood, leaves, branches, etc.) that can effectively participate in the combustion process within the area represented by the current grid, usually expressed as the mass of combustible material per unit area (e.g., kilograms per square meter, kg / m²). Net fuel load differs from total fuel load, which may include all types of fuel within the area represented by the current grid, including those that cannot effectively participate in the combustion process due to excessive moisture, overly compacted structure, or burial in the soil. In contrast, net fuel load focuses more on fuels that are actually combustible and can significantly influence the spread of fire. Net fuel load can be determined using the following formula:

[0096]

[0097] In the formula, It is the net fuel load. It represents the dry fuel load corresponding to the fuel within the area represented by the current grid. It represents the total mineral content of the fuel within the area represented by the current grid.

[0098] For example, calorific value can be the amount of heat released when a unit mass of fuel is completely burned, usually expressed in joules per gram (J / g) or kilojoules per kilogram (kJ / kg), and is used to reflect the energy density of the fuel. A higher calorific value means that the fuel releases more heat (i.e., energy) when burned, given the same mass.

[0099] For example, the humidity damping coefficient can be an adjustment factor representing the degree to which combustion efficiency and reaction rate decrease as fuel humidity increases, reflecting the inhibitory effect of fuel humidity on the combustion process. For instance, when fuel humidity is high, moisture absorbs the heat generated by combustion, delaying the fuel from reaching the temperature required for ignition, thereby slowing down the combustion rate. Preferably, the humidity damping coefficient can be determined by the following formula:

[0100]

[0101] In the formula, It is the humidity damping coefficient. This represents the current water content of the fuel within the area represented by the current grid. This is a specific humidity extinction threshold (i.e., a critical value), which can be set according to actual conditions. When the fuel moisture content exceeds this threshold, the ignition point may not be able to be maintained because the moisture absorbs a large amount of heat energy. It should be noted that the calculation formula for the humidity damping coefficient may vary depending on different models and application scenarios, and no specific restrictions are imposed here.

[0102] For example, the mineral damping coefficient is an adjustment factor used to measure the inhibitory effect of the mineral content in fuel on the combustion rate, reflecting the degree of influence of the mineral content in the fuel on the reaction rate. If the proportion of minerals in the fuel is high, the mineral damping coefficient is large, and combustion is more inhibited, resulting in a slower ignition point spread rate. Conversely, if the mineral content in the fuel is low, the mineral damping coefficient is low, and the combustion process is relatively unaffected, allowing the ignition point to spread at a faster rate. Preferably, the mineral damping coefficient can be determined by the following formula:

[0103]

[0104] In the formula, It is the mineral damping coefficient. This represents the effective mineral content of the fuel within the area depicted by the current grid. Effective mineral content refers to the proportion of minerals that actually affect combustion efficiency under combustion conditions. It should be noted that the calculation of the mineral damping coefficient may vary depending on the model and can take various forms, such as linear, exponential, or power-law relationships, depending on the model's assumptions and validated experimental data. No specific limitations are imposed here.

[0105] The flux coefficient mentioned above can be a parameter describing the energy transfer efficiency during the spread of an ignition point. It is used to quantify the energy (such as heat) released to the surrounding environment during fuel combustion and its impact on the spread rate of the ignition point. This flux coefficient comprehensively considers the flame geometry, fuel packing structure, and heat transfer mechanisms during combustion. The denser the fuel packing and the larger the specific surface area, the lower the flux coefficient of ignition point spread may be, and vice versa. The flux coefficient can be determined by the following formula:

[0106]

[0107] In the formula, It is the flux coefficient. It is the ratio of the surface area to the volume of fuel within the region represented by the current grid. It is the total packing ratio of all fuels in the area represented by the current grid, and the specific calculation formula is shown in the above embodiment.

[0108] The aforementioned bulk density, also known as true density or absolute density, can be the dry mass per unit volume of the fuel within the area represented by the current grid, excluding all internal voids and pores. It is used to reflect the compactness and mass distribution of the fuel and is not affected by external factors such as packing method, moisture content, or surrounding airflow.

[0109] The effective calorific number (ECN) can be a parameter describing the efficiency of a fuel's absorption and conversion of energy (such as thermal energy). It is primarily used to quantify the portion of the fuel that can be effectively converted into the thermal energy required to propel the ignition point during combustion. Generally, a fuel with a high ECN means that it can convert chemical energy into thermal energy more efficiently during combustion, and less energy is lost inefficiently, which typically leads to an increased rate of ignition point propagation. The ECN can be determined using the following formula:

[0110]

[0111] In the formula, It is the effective heating number. It is the ratio of the surface area to the volume of fuel within the region represented by the current grid. The specific parameters in the formula can be adjusted according to the actual situation.

[0112] The aforementioned pre-ignition heat can be considered as the minimum amount of heat that fuel in the area represented by the current grid needs to absorb before reaching its auto-ignition temperature to initiate combustion. It reflects the heat threshold at which fuel absorbs energy (such as heat) from the surrounding environment until pyrolysis and ignition (i.e., the appearance of an ignition point). The magnitude of the pre-ignition heat is influenced by various factors, including the physical properties of the fuel (such as density, moisture content, and particle size), chemical composition (such as volatile matter and fixed carbon content), and environmental conditions (such as temperature, humidity, and wind speed). Generally, fuels containing more volatile matter and less moisture may have a lower pre-ignition heat; while fuels with high density and high moisture content typically have a higher pre-ignition heat. In the embodiments of this application, if the heat transferred from the ignition point to the current grid reaches the pre-ignition heat threshold of the fuel in the area represented by the current grid during ignition point propagation, then an ignition point will appear in the current grid. Preferably, the pre-ignition heat can be determined by the following formula:

[0113]

[0114] In the formula, It is the heat of pre-combustion. This represents the current moisture content of the fuel within the area represented by the current grid. It should be noted that the calculation of pre-combustion heat is typically based on experimental data, obtained by conducting combustion tests on different types of fuels and measuring the energy required for them to absorb heat from the environment until ignition. The specific parameters in the above formula can be adjusted based on actual experimental data, and are not specifically limited here.

[0115] In this embodiment, the first parameter value is determined by summing a preset value with the terrain factor and wind speed factor to reflect the direct impact of environmental conditions on fire spread. Then, the second parameter value is calculated by multiplying the fuel reaction intensity within the current grid area by the flux coefficient of the ignition point during the spread process. The reaction intensity and flux coefficient together describe the fuel combustion efficiency and energy transfer rate. Simultaneously, the third parameter value is determined based on the product of the fuel bulk density, the effective heating number of the current grid, and the pre-combustion heat. These parameters comprehensively consider the physical properties of the fuel and the energy requirements for combustion. Finally, by combining the first, second, and third parameter values, the first spread rate is calculated, accurately reflecting the fire spread rate within a specific grid area.

[0116] As an optional implementation, determining the first propagation rate based on the first parameter value, the second parameter value, and the third parameter value includes: determining the product of the first parameter value and the second parameter value as the first product; and determining the ratio of the first product to the third parameter value as the first propagation rate.

[0117] For example, the first spread rate can be determined using the following formula:

[0118]

[0119] In the formula, It is the fastest rate of spread. It represents the reaction intensity of the fuel within the area represented by the current grid. It is the flux coefficient during the spread of the fire from the ignition point. It is the value of the second parameter. It is the wind speed factor. It is a topographic factor. It is the value of the first parameter. It is the volume density of fuel within the region represented by the current grid. This is the number of effective heaters in the current grid. This is the pre-combustion heat of the current grid. It is the value of the third parameter.

[0120] By effectively integrating the dynamic influencing factors of topography, meteorology, and vegetation cover, the spread potential of ignition points under different fuel types and environmental conditions can be assessed more accurately, ensuring the dynamism and accuracy of the prediction process and contributing to the development of effective fire prevention measures and response plans.

[0121] As an optional implementation, a second spread rate is determined based on a second part of the spread parameter values ​​in a set of spread parameter values, which includes: obtaining an initial spread rate from the ignition point from the first grid to the current grid; determining a fuel type correction coefficient, a wind speed correction coefficient, and a terrain correction coefficient for the fuel in the area represented by the current grid, wherein the second part of the spread parameter values ​​includes a fuel type correction coefficient; and determining the product of the initial spread rate, the fuel type correction coefficient, the wind speed correction coefficient, and the terrain correction coefficient as the second spread rate.

[0122] The initial spread rate mentioned above can be considered as the speed at which a fire spreads from the ignition point to the current grid under specific environmental conditions. This rate is influenced by various factors, primarily including fuel type, fuel arrangement, wind speed, wind direction, relative humidity, terrain slope, and daily maximum temperature. The calculation of the initial spread rate is usually based on a comprehensive assessment of these factors. For example, the initial spread rate can be determined using the following formula:

[0123]

[0124] In the formula, It is the initial spread rate. The highest temperature of the day; the higher the temperature, the easier it is for fuel to ignite, and the faster the fire can spread. The average wind speed of the day; the higher the wind speed, the faster the fire spreads. It is 100 - minimum daily relative humidity, expressed as a percentage. The lower the humidity, the drier the fuel and the easier it is to burn. , , , It is a constant value, and the specific value is determined based on the actual situation.

[0125] The aforementioned fuel type correction factor can be a parameter used to adjust the ignition point spread rate to reflect the combustion characteristics of different fuel types. Since the combustion rate, calorific value, thermal conductivity, and response to wind speed and terrain can vary significantly for each fuel, a fuel type correction factor is needed to differentiate and adapt to the effects of various fuel types in order to more accurately predict fire spread. In practical applications, the fuel type correction factor is usually a constant value, determined based on fuel classification (e.g., herbaceous, shrub, understory combustibles) and detailed fuel characteristics (e.g., moisture content, particle size distribution, bulk density).

[0126] The aforementioned wind speed correction factor is a key parameter used to adjust the spread rate of a fire ignition point. It can accelerate or slow down the spread of the fire, change its direction, etc., and represents the percentage increase or decrease in the fire spread rate as a function of wind speed, reflecting the degree of influence of wind speed on the spread of the fire ignition point. Generally, an increase in wind speed will accelerate the spread of the fire ignition point. Preferably, the wind speed correction factor can be determined by the following formula:

[0127]

[0128] In the formula, It is the wind speed correction factor. This represents the wind speed in the current grid (or the first grid), where the wind speed in the first grid is the same as the wind speed in the current grid. It should be noted that the specific formula for calculating the wind speed correction factor may vary depending on the model, and is not specifically limited here.

[0129] The aforementioned terrain correction coefficient can be used to adjust the spread rate of a fire point, reflecting the influence of terrain slope on the spread of the fire point. It is usually determined based on the slope; the steeper the slope, the higher the coefficient may be. For example, in uphill areas, the fire point tends to spread faster; while in downhill areas, the spread of the fire point may be relatively slower. Preferably, the terrain correction coefficient can be determined by the following formula:

[0130]

[0131] In the formula, It is the terrain correction factor. This refers to the terrain slope, which can be determined by the ratio of the terrain elevation difference to the distance. The terrain elevation difference can be the difference in elevation between the center point of the first grid and the center point of the current grid, and the distance can be the straight-line distance between the center points of the first and second grids. It should be noted that the values ​​of the constants in the above formula depend on the experimental data and the model validation results, and are not specifically limited here.

[0132] In this embodiment, the initial spread velocity of the fire point from the first grid to the current grid is first obtained. Then, considering the influence of different fuel types on the spread of the fire point, a fuel type correction coefficient for the fuel in the area represented by the current grid is determined. Simultaneously, the enhancing effect of wind direction and wind speed on the spread velocity of the fire point is evaluated, and the influence of terrain slope on the spread velocity of the fire point is analyzed to determine the wind speed correction coefficient and the terrain correction coefficient for the current grid. The correction coefficients are multiplied by the initial spread velocity to obtain the second spread velocity. For example, the second spread velocity can be determined using the following formula:

[0133]

[0134] In the formula, It is the second fastest rate of spread. It is the initial spread rate of the fire from the ignition point to the current grid. It is the fuel type correction factor for the fuel within the area represented by the current grid. This is the wind speed correction factor for the current grid. It is the terrain correction factor for the current grid.

[0135] The above operations visually reflect the actual spread rate of a fire from the first grid to the current grid under specific meteorological conditions, terrain features, and vegetation distribution. This refined calculation of spread rate allows for a more accurate simulation of the fire's path and speed, providing more scientific and real-time decision support for forest fire emergency response.

[0136] As an optional implementation, based on a set of expected spread times, predicting the grid in a set of grids that will be the earliest to ignite after the first grid ignites includes: determining the minimum expected spread time in the set of expected spread times; and determining the grid in the set of grids that corresponds to the minimum expected spread time as the grid that will be the earliest to ignite after the first grid ignites.

[0137] For example, such as Figure 4As shown, when grid 33 is the first grid, the grids adjacent to the first grid (including grids 22, 23, 24, 32, 34, 42, 43, and 44) ​​that have not yet developed an ignition point are identified as a group of grids. At this time, a group of grids can be grids 22, 23, 24, 32, 34, 42, 43, and 44. The estimated spread time from the ignition point from the first grid to the current grid is calculated for each of these grids, resulting in a group of estimated spread times, including t22, t23, t24, t32, t34, t42, t43, and t44. Then, the smallest estimated spread time in the group of estimated spread times is found to be t43. At this time, the grid corresponding to t43 (i.e., grid 43) is determined as the grid that develops an ignition point earliest after the first grid.

[0138] Through the above operations, and through meticulous gridding processing, complex geospatial data is transformed into unified grid data, further optimizing the accuracy and practicality of fire spread prediction. This enables the rapid location of the fire spread front, providing fire prevention decision-makers with immediate alerts and hotspot information.

[0139] As an optional implementation, the method further includes: if there is a third grid in the grid set whose expected spread time is earlier than the minimum expected spread time, the third grid is identified as the grid in the grid set that has the earliest ignition point after the first grid.

[0140] In this embodiment of the application, after determining a set of expected spread times, it is also possible to analyze the expected spread times of other grids outside of the set of grids. If there is a third grid in the set of grids, and the expected spread time of the third grid is earlier than the minimum expected spread time, then the third grid needs to be regarded as the grid that first appears to have an ignition point after the first grid.

[0141] The above operations effectively optimized the order of fire spread prediction, ensuring that the algorithm could prioritize areas with higher spread risk, thereby improving prediction efficiency and accuracy. Furthermore, by identifying the critical paths and areas of fire spread in advance, fire prevention personnel can allocate resources more precisely, strengthen early warning and response measures, and reduce forest losses.

[0142] As an optional implementation, before determining the estimated spread time from the ignition point to each grid in the set of grids and obtaining a set of estimated spread times, the above method further includes: obtaining the grids in the grid set that are adjacent to the first grid and have not yet had an ignition point, thus obtaining multiple adjacent grids; determining the multiple adjacent grids as a set of grids, or determining the grids in the multiple adjacent grids that do not have firebreaks as a set of grids.

[0143] The aforementioned fire barriers can be used to prevent or slow the spread of fire by eliminating or reducing fuel. Designing and timely deployment of fire barriers is an important strategy for reducing the scope of fire damage and improving fire extinguishing efficiency.

[0144] In this embodiment of the application, when a group of grids adjacent to the first grid and not yet occupied by an ignition point are pre-screened before the spread prediction, multiple grids adjacent to the first grid and not yet occupied by an ignition point can be directly determined as a group of grids, or the grids without firebreaks among the multiple grids adjacent to the first grid and not yet occupied by an ignition point can be determined as a group of grids.

[0145] Example, Figure 5 This is a schematic diagram of the spread of the ignition point according to an embodiment of this application. Figure 2 ,like Figure 5 As shown, since fire-resistant strips were pre-installed in multiple grids (including grids 14, 22, 23, 32, and 41), and grids with fire-resistant strips will not have ignition points, when determining a group of grids, first determine multiple grids adjacent to the first grid (grid 33) that have not yet had ignition points (including grids 22, 23, 24, 32, 34, 42, 43, and 44). Then, remove the grids with fire-resistant strips installed in the multiple grids, and retain the grids without fire-resistant strips as a group of grids, that is, grids 24, 34, 42, 43, and 44 as a group of grids.

[0146] By taking into account the actual situation of fire prevention measures, grids that are already burning or have firebreaks are excluded. This allows for the prediction of the spread of fire ignition points, ensuring that the calculation of subsequent spread predictions is limited to potentially combustible areas. This avoids ineffective calculations of firebreak areas, making the prediction model closer to real-world forest fire prevention scenarios, enhancing the system's practicality and decision support capabilities, and improving prediction efficiency and accuracy. Furthermore, the grid selection rules can be flexibly adjusted according to different fire prevention needs and strategies, further optimizing the accuracy and timeliness of spread prediction.

[0147] As an alternative implementation method, taking forest fires as an example, Figure 6 This is a propagation prediction process based on embodiments of this application. Figure 1 ,like Figure 6 As shown, the specific process is as follows:

[0148] Step S601: Obtain remote sensing images before and after the fire, and extract the true range of the fire (i.e. the range where the ignition point has appeared) f1 and the spread contour based on the remote sensing images before and after the fire.

[0149] Step S602: Analyze the remote sensing data before and after the fire, obtain the terrain height information of each location in the area collected by the remote sensing images, as well as the vegetation cover data, so as to convert the map data into various types of data and information f2.

[0150] Step S603: Collect meteorological information of the fire-affected area, including wind speed, wind direction, daily maximum temperature, relative humidity, etc., and generate meteorological data w;

[0151] Step S604: If a fire barrier has been installed in the fire-affected area, obtain the installation status g of the fire barrier. If it has not been installed, skip this step and proceed directly to step S605.

[0152] Step S605: Based on the area where the fire originated, the remote sensing image (including terrain height information and vegetation cover data obtained from the remote sensing image) is cropped so that the cropped remote sensing image contains a suitable area (i.e., the area containing the fire origin). Simultaneously, this area is divided into multiple grids according to a unified resolution and range standard, and each grid is numbered, thus achieving the gridding of the remote sensing image (e.g., ...). Figure 3 As shown in the figure, each grid contains terrain height information, vegetation cover data (or information), and combustion status information for the area represented by the grid. Simultaneously, based on the mapping relationship between vegetation and fuel, the gridded vegetation cover data is converted into Wang Zhengfei fuel distribution grids and Rothermel fuel distribution grids, respectively. Meteorological data is also gridded using the same method to obtain wind speed and wind direction grids. Finally, all the above gridded data are integrated into a unified simulation grid (i.e., grid set) x1, realizing data gridding. Each grid in the simulation grid contains terrain height information, vegetation cover data (or information), combustion status information, meteorological information, and other information for the area represented by the grid.

[0153] Step S606: Initialize the prediction model, set the model's stopping conditions, and input the simulation mesh into the initialized prediction model for prediction.

[0154] Step S607: Based on the relevant data in the simulation grid and the model's stopping conditions and other parameters x2 (where x2 includes x1), predict the spread of the ignition point. Specifically, this includes: finding the next cell X (i.e., the first grid) to be ignited (i.e., the ignition point appears) based on the most recent ignition time (i.e., the latest ignition time), igniting cell X (i.e., assuming that the ignition point has already appeared in the grid), and finding the neighbors of cell X (i.e., a group of grids), calculating the ignition time from cell X to each neighboring cell (i.e., a group of expected spread times), and then determining the next cell x3 to be ignited after cell X (i.e., the earliest ignition point to appear after the ignition point appears in the first grid) based on the ignition time.

[0155] Step S608: Output the final prediction result based on the cells determined by the model. The final prediction result can be an image or multiple data points calculated based on the next cell to be ignited after the determined cell X, such as the calculated burned area. For example, the prediction result can be as follows: Figure 4 or Figure 5 As shown.

[0156] Example 2:

[0157] In this application, based on the single spread prediction of the ignition point in the above embodiment one, the spread of the ignition point can be predicted multiple times, thereby predicting the area where the ignition point will appear within a certain period of time. The specific implementation method is shown in the following steps.

[0158] As an optional implementation, the above method includes: repeatedly performing a prediction operation until a preset condition is met, wherein the prediction operation includes: determining the grid where the latest ignition point appears in the grid set to obtain a first grid, wherein the grid set includes multiple grids obtained by dividing the area containing the ignition point; if the grids adjacent to the first grid in the grid set that have not yet ignited a point form a group of grids, determining the estimated spread time of the ignition point from the first grid to each grid in the group of grids to obtain a group of estimated spread times; based on the group of estimated spread times, predicting the grid where the earliest ignition point appears after the ignition point appears in the first grid in the group of grids, and taking the predicted grid as the grid where the latest ignition point appears; and determining the spread path of the ignition point based on each predicted grid.

[0159] The aforementioned prediction operation can be used to simulate the spread of a fire point. This prediction operation is an iterative process that continuously predicts the next grid where a fire point will appear, as well as the estimated spread time of the fire point in that grid, thereby simulating the spread path of the fire point.

[0160] The aforementioned grid set can be a collection of multiple grids (or grid cells) obtained by dividing geospatial data (such as remote sensing images, elevation, vegetation cover, etc.) according to a unified resolution and extent standard. Each grid can contain specific information about the area it represents, such as elevation and vegetation cover type. Dividing the data into grids facilitates data processing, analysis, and visualization of the collected data. A specific illustration can be shown below. Figure 3 As shown.

[0161] The first grid mentioned above can be the grid where the fire point most recently appeared in the grid set, that is, the most recently appeared fire point when the fire spread prediction is performed. For example, if the current fire spread prediction is performed at 12:00, then the fire point that last appeared before 12:00 (such as appearing at 11:59) is defined as the most recently appeared fire point, and the grid where the most recently appeared fire point is located is the first grid.

[0162] The aforementioned set of grids can be a collection of grids that have not yet shown an ignition point among the grids adjacent to the first grid. For example, after the collected data is gridded, each grid will contain the combustion state of the area represented by that grid (i.e., whether an ignition point has appeared). If the grid has not yet shown an ignition point (e.g., unburned state) or the grid has shown an ignition point (e.g., burning state or burnt-out state), then, based on the combustion state of each grid, the grids that have not yet shown an ignition point among the 8 grids surrounding the first grid can be determined in the grid set, thus obtaining a set of grids.

[0163] The predicted spread time can be the time when the ignition point appears in the area represented by the grid (i.e., the grid). This time can be a specific moment, such as 11:00, 11:05, 11:05:35, etc., without any specific restrictions.

[0164] In the application embodiment, at the beginning of each iteration, the first grid of the newly appearing ignition point in the location grid set relative to the initial time of this iteration is identified. Then, a group of grids adjacent to the first grid is analyzed, and the estimated propagation time of the ignition point from the first grid to each grid in the group is calculated. Based on the obtained multiple estimated propagation times, the grid where the earliest ignition point appears after the first grid is identified is determined, and this predicted grid is used as the first grid of the newly appearing ignition point in the next iteration. The specific prediction method in each iteration can be as shown in Embodiment 1 above.

[0165] It should be noted that, under normal circumstances, the grid corresponding to the smallest expected spread time in a set of calculated expected spread times is determined as the grid where the ignition point first appears after the first grid. If there is a third grid in the grid set whose expected spread time is earlier than the smallest expected spread time, then the third grid is determined as the grid where the ignition point first appears after the first grid. If there is an expected spread time in the expected spread times calculated in the historical iteration process that is earlier than all the expected spread times calculated in the current iteration, then that expected spread time is determined as the grid where the ignition point first appears. For details, please refer to the description of the following embodiments.

[0166] Through the above operations, by continuously predicting new ignition points and spread times, a dynamic path and pattern of fire spread are gradually constructed, thereby enabling a refined dynamic simulation of the fire spread process. This more accurately reflects the real mechanism of fire spread, improves the accuracy of fire spread prediction, and provides a scientific basis for early warning and emergency response to fires.

[0167] As an optional implementation, the preset conditions include at least one of the following: the number of times the prediction operation is executed is greater than or equal to a preset number; the total execution time of repeatedly executing the prediction operation is greater than or equal to a preset duration; the total number of predicted grids is greater than or equal to a preset number; and the total area of ​​predicted grids is greater than or equal to a preset area.

[0168] In this embodiment of the application, the aforementioned preset condition can be a stop condition for repeatedly executing the prediction operation. That is, when the preset condition is met, the prediction of the spread of the ignition point is stopped. The preset condition can be that the prediction time of the model (i.e., the total execution time) reaches a preset time, the area of ​​the area to be burned predicted by the model (i.e., the total area) reaches a preset area, the number of burning cells predicted by the model (i.e., the total number) reaches a preset number, or the number of model iterations (i.e., the number of executions) reaches a preset number, etc. The specific preset condition can be set based on the actual situation and is not specifically limited here.

[0169] By performing the above operations and setting preset conditions in advance, the scope and duration of the simulation can be effectively controlled, saving computing resources while ensuring the relevance and practicality of the prediction results. In addition, it can provide quantitative data to evaluate the effectiveness of fire prevention measures, study the characteristics of fire spread, and thus help with advance planning and preparation.

[0170] As an optional implementation, Figure 7 This is a propagation prediction process based on embodiments of this application. Figure 2 ,like Figure 7 As shown, the specific process is as follows:

[0171] Step S701: Obtain remote sensing images before and after the fire, and extract the true range of the fire (i.e. the range where the ignition point has appeared) f1 and the spread contour based on the remote sensing images before and after the fire.

[0172] Step S702: Analyze the remote sensing data before and after the fire, obtain the terrain height information of each location in the area collected by the remote sensing images, as well as the vegetation cover data, so as to convert the map data into various types of data and information f2.

[0173] Step S703: Collect meteorological information of the fire-affected area, including wind speed, wind direction, daily maximum temperature, relative humidity, etc., and generate meteorological data w;

[0174] Step S704: If a fire barrier has been installed in the fire-affected area, obtain the installation status g of the fire barrier. If it has not been installed, this step can be skipped and step S605 can be executed directly.

[0175] Step S705: Based on the area where the fire originated, the remote sensing image (including terrain height information and vegetation cover data obtained from the remote sensing image) is cropped so that the cropped remote sensing image contains a suitable area (i.e., the area containing the fire origin). Simultaneously, this area is divided into multiple grids according to a unified resolution and range standard, and each grid is numbered, thus achieving the gridding of the remote sensing image (e.g., ...). Figure 3 As shown in the figure, each grid contains terrain height information, vegetation cover data (or information), and combustion status information for the area represented by the grid. Simultaneously, based on the mapping relationship between vegetation and fuel, the gridded vegetation cover data is converted into Wang Zhengfei fuel distribution grids and Rothermel fuel distribution grids, respectively. Meteorological data is also gridded using the same method to obtain wind speed and wind direction grids. Finally, all the above gridded data are integrated into a unified simulation grid (i.e., grid set) x1, realizing data gridding. Each grid in the simulation grid contains terrain height information, vegetation cover data (or information), combustion status information, meteorological information, and other information for the area represented by the grid.

[0176] Step S706: Initialize the prediction model by setting the model's stopping conditions (i.e., preset conditions), save interval, firebreak time, etc., and input the simulation mesh into the initialized prediction model for prediction.

[0177] For example, stopping conditions may include: the model's prediction time reaches a preset time, the area of ​​the area to be burned predicted by the model reaches a preset area, the number of burned cells predicted by the model reaches a preset number, or the number of model iterations reaches a preset number, etc.

[0178] For example, the save interval can be the interval at which the system saves the intermediate data predicted by the model. For instance, the model calculates and saves the predicted data once after every 5 rounds of prediction, or the model calculates and saves the predicted data once every 5 minutes of operation.

[0179] For example, the fire barrier time can be the expected effective time of the fire barrier. The fire barrier can be set to take effect before the model prediction, or it can be set to take effect at a certain point in the model prediction process. For example, if the model starts prediction at 8 o'clock and the fire barrier is expected to take effect at 9 o'clock, then before 9 o'clock, the model does not need to consider the influence of the fire barrier when making predictions. Only after 9 o'clock does the model need to consider the influence of the fire barrier when making predictions.

[0180] Step S707, based on relevant data in the simulation mesh and parameters x2 (where x2 includes x1) such as the model's stopping conditions, save interval, and firebreak time, predict the spread of the ignition point, specifically including:

[0181] (1) In the case where the fire barrier is not in effect (e.g.) Figure 8 (as shown)

[0182] In the first iteration:

[0183] Based on the most recent ignition time (i.e., the latest ignition moment), find the next grid to be ignited (i.e., the grid where an ignition point appears), 33 (i.e., the first grid). Ignite grid 33 (i.e., assume that an ignition point has appeared in this grid), and use grid 33 as the center grid. Determine a group of grids adjacent to grid 33 that have not yet ignited (including grids 22, 23, 24, 32, 34, 42, 43, and 44). Calculate the distance between grid 33 and each grid in the group (i.e., the current grid), as well as the spread speed of the ignition point from grid 33 to each grid (i.e., the current grid). Using the distance and spread speed, determine the estimated spread time for each grid point, resulting in a set of estimated spread times (including t22). （1） t23 （1） t24 （1） t32 （1） t34 （1） t42 （1） t43 （1） t44 （1） ); then, the minimum expected ignition time (e.g., t43) will be used. （1） The corresponding grid is used as the next grid where an ignition point occurs, and as the first grid that was most recently ignited in the next iteration;

[0184] In the second iteration:

[0185] Based on the most recent ignition time (i.e., the latest ignition moment), find the next grid to be ignited (i.e., the grid where an ignition point appears), 43 (i.e., the first grid). Ignite grid 43 (i.e., assume that an ignition point has appeared in this grid), and use grid 43 as the center grid. Determine a group of grids adjacent to grid 43 that have not yet ignited (including grids 32, 34, 42, 44, 52, 53, and 54). Calculate the distance between grid 43 and each grid in the group (i.e., the current grid), as well as the spread rate of the ignition point from grid 43 to each grid (i.e., the current grid). Using the distance and spread rate, determine the estimated spread time for each grid point, resulting in a set of estimated spread times (including t32). （2） t34 （2） t42 （2） t44 （2） t52 （2） ,t53 （2） t54 （2） Then, the minimum expected ignition time (e.g., t53) will be determined. （2） The corresponding grid is used as the next grid where an ignition point occurs, and as the first grid that was most recently ignited in the next iteration;

[0186] It should be noted that if the estimated spread time calculated in the first iteration contains a portion earlier than the total estimated spread time calculated in the second iteration, such as t24... （1） Earlier than T32 （2） t34 （2） t42 （2） t44 （2） t52 （2） ,t53 （2） t54 （2） The entire time in, at this point, will be t24. （1） The corresponding grid 24 (i.e., the third grid) is used as the next grid where an ignition point occurs, and as the first grid of the most recent ignition in the next iteration. The propagation prediction result is as follows: Figure 9 As shown;

[0187] Furthermore, after calculating the expected spread time of the grid in each iteration, it is necessary to evaluate the calculated expected spread time and update the expected spread time of each grid. For example, if the expected spread time calculated in a subsequent iteration is earlier than the expected spread time calculated in a previous iteration, the expected spread time of the grid is updated. For instance, in the second iteration, the expected spread time t32 of grid 32 is calculated. （2） The predicted propagation time t32 for grid 32 was calculated earlier than in the first iteration. （1）Then the expected propagation time t32 of grid 32 calculated in the second iteration is used. （2） The estimated propagation time for grid 32 is updated to t32. （2） The expected propagation time for grid 32 is used as the reference time; otherwise, the expected propagation time for grid 32 is not updated, i.e., it is still the expected propagation time t32 calculated in the first iteration. （1） As the expected spread time for grid 32;

[0188] Then, repeat the above iterative operation in a loop;

[0189] (2) When the fire-resistant strip is in effect (e.g.) Figure 10 As shown in the diagram, fire-resistant strips are installed at grids 14, 22, 23, 32, and 41.

[0190] In the first iteration:

[0191] Based on the most recent ignition time (i.e., the latest ignition moment), find the next grid to be ignited (i.e., the grid where the ignition point appears), Grid 33 (i.e., the first grid), ignite Grid 33 (i.e., presuppose that the grid has already had an ignition point), and use Grid 33 as the center grid. Determine multiple grids adjacent to Grid 33 (including Grid 22, Grid 23, Grid 24, Grid 32, Grid 34, Grid 42, Grid 43, Grid 44). Among these grids, find a group of grids that have not yet had an ignition point and have not set up a firebreak (including Grid 24, Grid 34, Grid 42, Grid 43, Grid 44). Calculate the distance between Grid 33 and each grid in the group (i.e., the current grid), as well as the spread speed of the ignition point from Grid 33 to each grid (i.e., the current grid). Using the distance and spread speed, determine the estimated spread time for each grid point, obtaining a set of estimated spread times (including t24). （1） t34 （1） t42 （1） t43 （1） t44 （1） ); then, the minimum expected ignition time (e.g., t43) will be used. （1） The corresponding grid is used as the next grid where an ignition point occurs, and as the first grid that was most recently ignited in the next iteration;

[0192] In the second iteration:

[0193] Based on the most recent ignition time (i.e., the latest ignition moment), find the next grid to be ignited (i.e., the grid where the ignition point appears), 43 (i.e., the first grid). Ignite grid 43 (i.e., presuppose that the grid has an ignition point), and use grid 43 as the center grid. Determine multiple grids adjacent to grid 43 (including grids 32, 33, 34, 42, 44, 52, 53, and 54). Among these grids, find a group of grids that have not yet had an ignition point and have not set up a firebreak (including grids 34, 42, 44, 52, 53, and 54). Calculate the distance between grid 43 and each grid in the group (i.e., the current grid), as well as the spread speed of the ignition point from grid 43 to each grid (i.e., the current grid). Using the distance and spread speed, determine the estimated spread time for each grid point, obtaining a set of estimated spread times (including t34). （2） t42 （2） t44 （2） t52 （2） ,t53 （2） t54 （2） Then, the minimum expected ignition time (e.g., t53) will be determined. （2） The corresponding grid is used as the next grid where an ignition point occurs, and as the first grid that was most recently ignited in the next iteration;

[0194] It should be noted that if there is an earlier predicted spread time than all predicted spread times calculated in the second iteration in the first iteration, then the grid corresponding to that predicted spread time (i.e., the third grid) should also be used as the grid where the ignition point appears next, and as the first grid of the most recent ignition in the next iteration; while the effective time of the fire barrier can be set in any iteration process, without specific restrictions here;

[0195] Furthermore, after calculating the expected spread time of the grid in each iteration, it is necessary to evaluate the calculated expected spread time and update the expected spread time of each grid. For example, if the expected spread time calculated in a subsequent iteration is earlier than the expected spread time calculated in a previous iteration, the expected spread time of the grid is updated. For instance, in the second iteration, the expected spread time t42 of grid 42 is calculated. （2） The predicted propagation time t42 for grid 42 was calculated earlier than in the first iteration. （1） Then the expected spread time t42 of grid 42 calculated in the second iteration is used. （2） The estimated propagation time for grid 42 is updated to t42. （2） The expected spread time for grid 42 is used as the reference time; otherwise, the expected spread time for grid 42 is not updated, i.e., it is still the expected spread time t42 calculated in the first iteration. （1）As the expected spread time for grid 42;

[0196] Then, repeat the above iterative operation in a loop;

[0197] Step S708: If the model prediction has not yet reached the stopping condition, but the saving interval is met, calculate the intermediate results based on the current prediction results of the model and save the intermediate results. For example, the intermediate results may include: spread profile, fire head parameters, ignition point sampling, fire velocity, combustion index, slope index, burned area, etc. Figure 8 For example, after the second iteration, the specific calculation method is as follows:

[0198] Spread profile: Based on the predicted grid where the ignition point will appear, profile detection is performed, and the largest profile is selected as the spread profile, that is, the overall profile of grid 33, grid 43 and grid 53.

[0199] Firehead parameters: Take the M cells with the highest spread rate among all the grids where ignition points have already appeared and where ignition points are about to appear on the boundary as the firehead positions. Calculate the spread rate of the ignition point from the firehead position to its adjacent grids. Take the direction with the highest spread rate as the firehead direction. That is, take the grid with the highest spread rate among grids 33, 43, and 53 (such as grid 53) as the firehead position. Determine the spread rate of the ignition point from grid 53 to its four adjacent grids (grids 42, 44, 52, and 54). Take the direction with the highest spread rate as the firehead direction.

[0200] Ignition point sampling: A percentage of samples are taken from all grids where ignition points have occurred and where ignition points are about to occur, according to a set threshold.

[0201] Fire speed: The ratio of the farthest distance between the ignition point and the fire head to the time it takes for the fire head to ignite is determined as the fire speed, that is, the ratio of the distance between grid 33 and grid 53 to the time it takes for the fire head to ignite.

[0202] Combustion Index: The mean and variance of the KS fuel coefficient of fuel in the regions represented by all grids that have ignition points and those that are about to ignite are used as the combustion index. Specifically, the mean and variance of the KS fuel coefficient of fuel in the regions represented by grids 33, 43, and 53 are used as the combustion index.

[0203] Slope index: The average slope between a grid and all its adjacent grids is taken as the slope of that grid. The slope between two grids can be taken as the ratio of the difference in terrain height between the center points of two grids to the distance between the center points of two grids. The mean and variance of the slopes of all grids that have ignition points and those that will ignite points are calculated as the slope index. Specifically, the mean and variance of the slopes of grids 33, 43, and 53 are taken as the slope index.

[0204] Fire area: Calculate the number of all grids where fire points have occurred and where fire points are about to occur, and multiply the area of ​​a single grid by the number of grids to get the fire area, i.e. the total area of ​​grids 33, 43 and 53.

[0205] Step S709: If the model prediction still meets the stopping condition, stop the iteration operation and the propagation is complete.

[0206] Step S710: Output the final prediction result based on the prediction results of each iteration of the model. The final prediction result can be an image or multiple data calculated based on the prediction results of each iteration of the model, such as spread profile, fire head parameters, ignition point sampling, fire speed, combustion index, slope index, and burned area.

[0207] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0208] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0209] According to another aspect of the embodiments of this application, a fire point spread prediction device is also provided. This fire point spread prediction device can be used to implement the fire point spread prediction method provided in the above embodiments, and will not be repeated hereafter. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0210] Figure 11 This is a structural block diagram of a fire ignition point spread prediction device according to an embodiment of this application, such as... Figure 11 As shown, the fire spread prediction device includes: a memory 1102, a processor 1104, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following operations: determining the grid in the grid set where the fire point has recently appeared, to obtain a first grid, wherein the grid set includes multiple grids obtained by dividing the area containing the fire point; when the grids in the grid set that are adjacent to the first grid and have not yet appeared as a group of grids, determining the estimated spread time of the fire point from the first grid to each grid in the group of grids, to obtain a set of estimated spread times; and based on the set of estimated spread times, predicting the grid in the group of grids where the fire point will appear earliest after the fire point appears in the first grid.

[0211] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: perform the following operations on each grid in a set of grids respectively to obtain a set of expected spread times, wherein each grid in the set of grids is the current grid when performing the following operations: determine a set of spread parameter values ​​for the current grid; and determine the expected spread time for the ignition point to spread from the first grid to the current grid based on the set of spread parameter values.

[0212] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: determine the distance between the center point of the first grid and the center point of the current grid; determine the spread rate of the fire from the first grid to the current grid based on a set of spread parameter values; and determine the estimated spread time of the fire from the first grid to the current grid based on the distance and the spread rate.

[0213] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: determining a first spread rate from the ignition point to the current grid based on a first portion of spread parameter values ​​in a set of spread parameter values, wherein the first portion of spread parameter values ​​is used to characterize the physical properties of the fuel in the area represented by the current grid; determining a second spread rate from the ignition point to the current grid based on a second portion of spread parameter values ​​in a set of spread parameter values, wherein the second portion of spread parameter values ​​is used to characterize the distribution characteristics of the fuel in the area containing the ignition point; and determining the spread rate as a weighted sum of the first spread rate and the second spread rate.

[0214] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: determine the terrain factor and wind speed factor of the current grid, wherein the terrain factor is used to represent the degree of influence of the terrain in the area represented by the current grid on the spread speed of the ignition point, and the wind speed factor is used to represent the degree of influence of the wind speed in the area represented by the current grid on the spread speed of the ignition point; and determine a first spread speed based on the first part of the spread parameter value, the terrain factor, and the wind speed factor.

[0215] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: determining the sum of a preset value, a terrain factor, and a wind speed factor as a first parameter value; determining the product of the reaction intensity of the fuel in the area represented by the current grid, the flux coefficient of the ignition point during the propagation process, and the first parameter value as a second parameter value, wherein the first part of the propagation parameter value includes the reaction intensity and the flux coefficient, the reaction intensity being used to represent the amount of energy released by the fuel during combustion per unit time and per unit area, and the flux coefficient being used to represent the amount of energy transferred by the ignition point during propagation per unit time and per unit area; determining the product of the volume density of the fuel in the area represented by the current grid, the effective heating number of the current grid, and the pre-combustion heat of the current grid as a third parameter value, wherein the first part of the propagation parameter value also includes the volume density, the effective heating number, and the pre-combustion heat, the effective heating number being used to represent the ratio of the energy used for heating and the energy used for maintaining the flame during combustion of the fuel in the area represented by the current grid, and the pre-combustion heat being used to represent the minimum energy required for the ignition point to appear in the current grid; and determining a first propagation speed based on the first parameter value, the second parameter value, and the third parameter value.

[0216] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: determine the product of the first parameter value and the second parameter value as a first product; and determine the ratio of the first product to the third parameter value as a first propagation rate.

[0217] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: obtain the initial spread rate of the fire point spreading from the first grid to the current grid; determine the fuel type correction coefficient, the wind speed correction coefficient, and the terrain correction coefficient of the fuel in the area represented by the current grid, wherein the second part of the spread parameter value includes the fuel type correction coefficient; and determine the product of the initial spread rate, the fuel type correction coefficient, the wind speed correction coefficient, and the terrain correction coefficient as the second spread rate.

[0218] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: obtain the moment when the ignition point appears in the first grid to obtain a first time; determine the ratio of distance to spread speed as a time interval; and determine the sum of the first time and the time interval as the estimated spread time for the ignition point to spread from the first grid to the current grid.

[0219] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: determine the minimum expected spread time among a set of expected spread times; and determine the grid in the set of grids that corresponds to the minimum expected spread time as the grid that first has an ignition point after the first grid has an ignition point.

[0220] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operation: if there is a third grid in the grid set whose expected spread time is earlier than the minimum expected spread time, the third grid is determined as the grid in the grid set that has the earliest ignition point after the first grid.

[0221] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: obtain the grids in the grid set that are adjacent to the first grid and have not yet had an ignition point, thereby obtaining multiple adjacent grids; determine the multiple adjacent grids as a group of grids, or determine the grids in the multiple adjacent grids that do not have firebreaks as a group of grids.

[0222] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: determine the grids in the grid set where an ignition point has occurred, and obtain multiple candidate grids; determine the time when an ignition point occurs in each of the multiple candidate grids, and obtain multiple ignition times corresponding one-to-one with the multiple candidate grids; determine the latest ignition time among the multiple ignition times; and determine the grid in the multiple candidate grids that corresponds to the latest ignition time as the first grid.

[0223] In an exemplary embodiment, when the processor 1104 executes the computer program, it is further configured to perform the following operations: repeatedly execute the prediction operation until a preset condition is met, wherein the prediction operation includes: determining the grid where the latest ignition point appears in the grid set to obtain a first grid, wherein the grid set includes multiple grids obtained by dividing the area containing the ignition point; when the grids adjacent to the first grid in the grid set that have not yet ignited a point form a group of grids, determining the estimated spread time of the ignition point from the first grid to each grid in the group of grids to obtain a group of estimated spread times; based on the group of estimated spread times, predicting the grid where the earliest ignition point appears after the first grid appears in the group of grids, and using the predicted grid as the grid where the latest ignition point appears; and determining the spread path of the ignition point based on each predicted grid.

[0224] In one exemplary embodiment, the preset conditions include at least one of the following: the number of times the prediction operation is executed is greater than or equal to a preset number; the total execution time of repeatedly executing the prediction operation is greater than or equal to a preset duration; the total number of predicted grids is greater than or equal to a preset number; and the total area of ​​predicted grids is greater than or equal to a preset area.

[0225] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0226] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program executes the steps in any of the above method embodiments when it is run.

[0227] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, ROMs, RAMs, portable hard drives, magnetic disks, or optical disks.

[0228] According to another aspect of the embodiments of this application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor is configured to perform the steps of any of the method embodiments described above via the computer program. In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0229] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0230] According to another aspect of the embodiments of this application, a computer program product is also provided, which includes a computer program / instructions containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit, it performs various functions provided in the embodiments of this application. The sequence numbers of the embodiments of this application above are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0231] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0232] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for predicting the spread of an ignition point, characterized in that, include: The grid where the latest ignition point appears is determined in the grid set to obtain the first grid, wherein the grid set includes multiple grids obtained by dividing the area containing the ignition point; In the case where the grids adjacent to the first grid in the grid set and where no ignition point has yet appeared are a group of grids, the estimated spread time of the ignition point from the first grid to each grid in the group of grids is determined to obtain a set of estimated spread times. Based on the set of predicted spread times, predict the grid in the set of grids that will be the earliest to develop an ignition point after the ignition point appears in the first grid.

2. The method according to claim 1, characterized in that, In the case where the grids adjacent to the first grid in the grid set that have not yet shown an ignition point form a group of grids, the estimated propagation time of the ignition point from the first grid to each grid in the group of grids is determined, resulting in a set of estimated propagation times, including: Perform the following operations on each grid in the set of grids to obtain the set of estimated spread times, wherein each grid in the set of grids is the current grid when performing the following operations: Determine a set of propagation parameter values ​​for the current mesh; Based on the set of spread parameter values, the estimated spread time for the fire to spread from the first grid to the current grid is determined.

3. The method according to claim 2, characterized in that, The step of determining the estimated propagation time of the fire from the ignition point to the current grid based on the set of propagation parameter values ​​includes: Determine the distance between the center point of the first grid and the center point of the current grid; Based on the set of spread parameter values, the spread rate of the fire from the first grid to the current grid is determined; Based on the distance and the spread rate, the estimated spread time for the fire to spread from the first grid to the current grid is determined.

4. The method according to claim 3, characterized in that, The step of determining the spread rate of the fire from the first grid to the current grid based on the set of spread parameter values ​​includes: Based on the first part of the spread parameter values ​​in the set of spread parameter values, a first spread velocity is determined for the spread of the ignition point from the first grid to the current grid, wherein the first part of the spread parameter values ​​is used to characterize the physical properties of the fuel in the area represented by the current grid; Based on the second part of the spread parameter values ​​in the set of spread parameter values, a second spread velocity is determined for the spread of the ignition point from the first grid to the current grid, wherein the second part of the spread parameter values ​​is used to characterize the distribution characteristics of fuel in the area containing the ignition point; The spread rate is determined by the weighted sum of the first spread rate and the second spread rate.

5. The method according to claim 4, characterized in that, Determining the first spread velocity of the fire spreading from the first grid to the current grid based on the first portion of the spread parameter values ​​in the set of spread parameter values ​​includes: Determine the terrain factor and wind speed factor of the current grid, wherein the terrain factor is used to represent the degree of influence of the terrain in the area represented by the current grid on the spread speed of the fire point, and the wind speed factor is used to represent the degree of influence of the wind speed in the area represented by the current grid on the spread speed of the fire point. The first spread rate is determined based on the first spread parameter values, the terrain factor, and the wind speed factor.

6. The method according to claim 5, characterized in that, Determining the first spread velocity based on the first spread parameter values, the terrain factor, and the wind speed factor includes: The sum of the preset value, the terrain factor, and the wind speed factor is determined as the first parameter value; The product of the reaction intensity of the fuel in the area represented by the current grid, the flux coefficient of the ignition point during the propagation process, and the first parameter value is determined as the second parameter value. The first part of the propagation parameter value includes the reaction intensity and the flux coefficient. The reaction intensity is used to represent the amount of energy released by the fuel during combustion per unit time and per unit area. The flux coefficient is used to represent the amount of energy transferred by the ignition point during propagation per unit time and per unit area. The product of the volumetric density of the fuel in the region represented by the current grid, the effective heating number of the current grid, and the pre-combustion heat of the current grid is determined as the third parameter value. The first part of the propagation parameter value also includes the volumetric density, the effective heating number, and the pre-combustion heat. The effective heating number is used to represent the ratio of the energy used for heating and the energy used to maintain the flame during the combustion process of the fuel in the region represented by the current grid. The pre-combustion heat is used to represent the minimum energy required for the current grid to reach the ignition point. The first spread rate is determined based on the first parameter value, the second parameter value, and the third parameter value.

7. The method according to claim 6, characterized in that, Determining the first spread rate based on the first parameter value, the second parameter value, and the third parameter value includes: The product of the first parameter value and the second parameter value is determined as the first product; The ratio of the first product to the value of the third parameter is determined as the first spread rate.

8. The method according to claim 4, characterized in that, Determining the second spread velocity of the fire from the first grid to the current grid based on the second part of the spread parameter values ​​in the set of spread parameter values ​​includes: Obtain the initial spread rate of the fire from the ignition point to the current grid; Determine the fuel type correction factor, the wind speed correction factor, and the terrain correction factor for the fuel within the area represented by the current grid, wherein the second part of the spread parameter value includes the fuel type correction factor; The product of the initial spread rate, the fuel type correction factor, the wind speed correction factor, and the terrain correction factor is determined as the second spread rate.

9. The method according to claim 3, characterized in that, Determining the estimated spread time from the ignition point to the current grid based on the distance and the spread rate includes: Obtain the moment when the ignition point appears in the first grid to obtain the first time; The ratio of the distance to the spread rate is defined as the time interval; The sum of the first time and the time interval is determined as the estimated propagation time for the fire to spread from the first grid to the current grid.

10. The method according to any one of claims 1 to 9, characterized in that, Based on the set of predicted spread times, the grid in the set of grids that predicts the earliest ignition point after the ignition point appears in the first grid includes: Determine the smallest expected spread time among the set of expected spread times; The grid in the set of grids that corresponds to the minimum expected spread time is determined as the grid that first develops an ignition point after the ignition point in the first grid.

11. The method according to claim 10, characterized in that, The method further includes: If there is a third grid in the grid set whose expected spread time is earlier than the minimum expected spread time, the third grid is determined as the grid in the grid set where the ignition point occurs earliest after the ignition point occurs in the first grid.

12. The method according to any one of claims 1 to 9, characterized in that, Before determining the estimated propagation time of the fire from the first grid to each grid in the set of grids, and obtaining a set of estimated propagation times, the method further includes: Obtain the grids in the grid set that are adjacent to the first grid and for which the ignition point has not yet appeared, thus obtaining multiple adjacent grids; The plurality of adjacent grids are defined as the group of grids, or the grids among the plurality of adjacent grids that do not have fire-resistant strips are defined as the group of grids.

13. The method according to any one of claims 1 to 9, characterized in that, The process of determining the grid where the latest ignition point appears in the grid set to obtain the first grid includes: In the grid set, the grids where ignition points have occurred are identified, resulting in multiple candidate grids; Determine the time when the ignition point occurs in each of the multiple candidate grids to obtain multiple ignition times that correspond one-to-one with the multiple candidate grids; Determine the latest fire time among the plurality of fire times; The grid corresponding to the latest ignition time among the multiple candidate grids is determined as the first grid.

14. The method according to claim 1, characterized in that, The method includes: The prediction operation is repeated until a preset condition is met. The prediction operation includes: determining the grid where the fire point has recently appeared in a grid set to obtain a first grid; wherein the grid set includes multiple grids obtained by dividing the area containing the fire point; if the grids adjacent to the first grid in the grid set that have not yet shown the fire point form a group of grids, determining the estimated spread time for the fire point to spread from the first grid to each grid in the group of grids to obtain a set of estimated spread times; based on the set of estimated spread times, predicting the grid in the group of grids where the fire point appears earliest after the fire point appears in the first grid, and using the predicted grid as the grid where the fire point has recently appeared. The spread path of the fire is determined based on the predicted grid points.

15. The method according to claim 14, characterized in that, The preset conditions include at least one of the following: The prediction operation is executed more than or equal to a preset number of times; The total execution time for repeatedly performing the prediction operation is greater than or equal to a preset duration; The total number of predicted grid cells is greater than or equal to the preset number; The total area of ​​all predicted grids is greater than or equal to the preset area.

16. A device for predicting the spread of an ignition point, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the following operations: The grid where the latest ignition point appears is determined in the grid set to obtain the first grid, wherein the grid set includes multiple grids obtained by dividing the area containing the ignition point; In the case where the grids adjacent to the first grid in the grid set and where no ignition point has yet appeared are a group of grids, the estimated spread time of the ignition point from the first grid to each grid in the group of grids is determined to obtain a set of estimated spread times. Based on the set of predicted spread times, predict the grid in the set of grids that will be the earliest to develop an ignition point after the ignition point appears in the first grid.

17. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 15.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 15.

19. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 15.

Images