Forest fire spreading prediction method, device and equipment and storage medium

Abstract

The invention provides a forest fire spreading prediction method, device and equipment and a storage medium, and the method comprises the steps: obtaining multispectral remote sensing data, DEM data and meteorological data of a first region in a current time period in response to a disaster occurrence signal; processing the multispectral remote sensing data, the DEM data and the meteorological data of the first area based on a Wang Zheng African and Mouyan Sensitivity Model combination model, and determining the current forest fire spreading speed of each cell in the real-time hazard range of the disaster; and processing the current forest fire spreading speed of each cell by adopting a cellular automaton algorithm to obtain a forest fire spreading prediction result of the first area in the current time period. According to the method, information such as combustible coefficient, slope angle and wind speed can be obtained through the multispectral remote sensing data, DEM data and meteorological data of the forest fire occurrence area, forest fire spreading simulation is carried out in combination with the Wang-Zheng-Not and Macrosensitivity widening combined model and the cellular automaton algorithm, the forest fire spreading simulation precision can be improved, and the application range of the forest fire spreading simulation can be widened.

Description

Technical Field

[0001] The present application belongs to the technical field of fire prediction, and specifically, relates to a method, device, equipment and storage medium for predicting the spread of forest fires. Background Art

[0002] Climate warming and the increase in extreme weather have increased the risk of forest fires in the world. A large number of highly destructive forest fires have posed a major threat to human society. Therefore, it is important to scientifically understand the mechanisms and laws of forest fire occurrence and development, and simulate and predict the spread of forest fires as soon as they occur. This is of great significance for fire emergency command and rescue, reducing casualties, and protecting people's lives and property safety to the greatest extent possible.

[0003] The current forest fire spread models can be roughly divided into the following categories: semi-mechanistic and semi-statistical models represented by Canada's forest fire spread model, physical mechanism models represented by the American Rothermel model, statistical models represented by Australia's McArthur model, and China's Wang Zhengfei model. The forest fire spread model proposed by Rothermel in the United States is a physical mechanism model based on the law of conservation of energy. The experimental model given by the Canadian forest fire forecasting system mainly focuses on the impact of slope on the speed of forest fire spread.

[0004] However, most of the current forest fire spread model predictions use a single model, such as using only algorithms such as cellular automata to simulate the spread of forest fires, without actually calculating the speed, intensity and other physical states of the forest fire spread, or using only a single Wang Zhengfei model combined with relevant geographical factors to calculate the speed of forest fire spread and then use simple rules to deduce the situation of forest fire spread. This single model has low prediction accuracy, cannot adapt to the complex actual geographical environment, and is difficult to meet the requirements of forest fire disaster relief. Summary of the invention

[0005] In view of the above problems, the present application aims to provide a forest fire spread prediction method, device, equipment and storage medium, which are used to solve the problems of low accuracy and limited scope of application of forest fire spread prediction methods in the prior art.

[0006] In a first aspect, the present application provides a forest fire spread prediction method, comprising:

[0007] In response to a signal of a disaster, multispectral remote sensing data, DEM data, and meteorological data of a first area in a current time period are acquired, wherein the first area is larger than a second area, and the second area is a final endangered area estimated based on the real-time endangered area of ​​the disaster;

[0008] Based on the combined model of Wang Zhengfei and Mao Xianmin, the multispectral remote sensing data, DEM data and meteorological data of the first area are processed to determine the current forest fire spread speed of each cell in the real-time endangered range of the disaster, where the cell is the area obtained by dividing the first area;

[0009] The cellular automaton algorithm is used to process the current forest fire spread speed of each cell to obtain the forest fire spread prediction result of the first area in the current time period.

[0010] In a possible embodiment, the multispectral remote sensing data, DEM data and meteorological data of the first area are processed based on the Wang Zhengfei and Mao Xianmin combined model to determine the current forest fire spread speed of each cell in the real-time endangered range of the disaster, specifically including:

[0011] Preprocessing the multispectral remote sensing data, DEM data and meteorological data of the first area to obtain the multispectral remote sensing data, DEM data and meteorological data of the second area;

[0012] Determine the combustible factor, slope angle, and wind speed based on multispectral remote sensing data, DEM data, and meteorological data of the second region;

[0013] The combined model of Wang Zhengfei and Mao Xianmin was used to process the combustible coefficient, slope angle and wind speed in the second area to obtain the current forest fire spread speed of each cell in the real-time endangered range of the disaster.

[0014] In a possible embodiment, the calculation method of the combustible coefficient of the second area includes:

[0015] determining a normalized difference vegetation index based on multispectral remote sensing data of a second region;

[0016] determining non-vegetated areas and different vegetation types in the vegetation areas of the second region according to the normalized difference vegetation index;

[0017] The combustible material coefficient of the second area is determined according to the combustible material coefficient table of different vegetation types.

[0018] In a possible embodiment, the Wang Zhengfei and Mao Xianmin combined model is used to process the combustible coefficient, slope angle and wind speed of the second area to obtain the current forest fire spread speed of each cell in the real-time endangered range of the disaster, including:

[0019] Determining the combustible material configuration pattern coefficient according to the combustible material coefficient of the second area;

[0020] The wind action coefficient is determined according to the angle between the wind speed direction in the second area and the direction of forest fire spread and the wind speed;

[0021] The slope adjustment coefficient is determined based on the slope angle and the angle between the slope direction and the direction of forest fire spread;

[0022] Determine the current forest fire spread speed for each cell in different forest fire spread directions.

[0023] In a possible embodiment, the cellular automaton algorithm is used to process the current forest fire spread speed of each cell to obtain the forest fire spread prediction result of the first area in the current time period, including:

[0024] Get the combustion status of the target cell in the current time period;

[0025] Determine the burning state of the target cell in the next time period according to the burning state of the target cell in the current time period, the current forest fire spreading speed of the target cell, the current forest fire spreading speed of the adjacent cells adjacent to the target cell, and the current forest fire spreading speed of the next adjacent cells adjacent to the target cell;

[0026] According to the combustion status of each of the target cells in the next time period, a forest fire spread prediction result of the first area in the current time period is obtained.

[0027] In a possible embodiment, determining the burning state of the target cell in the next time period according to the burning state of the target cell in the current time period, the current forest fire spread speed of the target cell, the current forest fire spread speed of the adjacent cells adjacent to the target cell, and the current forest fire spread speed of the secondary adjacent cells adjacent to the target cell specifically includes:

[0028] The combustion state of the target cell in the next time period is determined by the following formula:

[0029]

[0030] Among them, t is the current time period, Δt is the time step of a spread, is the combustion state of the target cell in the current time period, is the combustion state of the target cell in the next time period, is the current forest fire spreading speed of the four adjacent cells of the target cell, is the current forest fire spread speed of the four secondary adjacent cells of the target cell, a is the side length of the cell, i is the horizontal coordinate of the target cell, and j is the vertical coordinate of the target cell.

[0031] In a possible embodiment, after the current forest fire spread speed of each cell is processed by the cellular automaton algorithm to obtain the forest fire spread prediction result of the first area in the current time period, the method further includes:

[0032] Synthesizing multispectral remote sensing data of different bands of the first region to obtain an image of the first region;

[0033] The forest fire spread prediction result of the first area is applied to the first area image to display the burned area.

[0034] In the second aspect, the present application also provides a forest fire spread prediction, including:

[0035] An acquisition module, configured to respond to a signal of a disaster occurrence and acquire multispectral remote sensing data, DEM data, and meteorological data of a first area in a current time period, wherein the first area is larger than a second area, and the second area is a final endangered area inferred according to a real-time endangered area of ​​the disaster;

[0036] A calculation module, for processing the multispectral remote sensing data, DEM data and meteorological data of the first region based on the Wang Zhengfei and Mao Xianmin combined model, and determining the current forest fire spread speed of each cell of the real-time endangered range of the disaster, wherein the cell is a region obtained by dividing the first region;

[0037] The prediction module is used to process the current forest fire spread speed of each cell using a cellular automaton model to obtain the forest fire spread prediction result of the first area in the current time period.

[0038] In a third aspect, the present application further provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0039] The memory stores computer-executable instructions;

[0040] The processor executes the computer-executable instructions stored in the memory to implement the forest fire spread prediction method described in any one of the first aspects above.

[0041] In a fourth aspect, the present application further provides a computer storage medium, wherein the computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the forest fire spread prediction method described in any one of the first aspects above.

[0042] The present application provides a method, device, equipment and storage medium for predicting the spread of forest fires. The method first obtains multispectral remote sensing data, DEM data and meteorological data of the first area in the current time period; then processes the multispectral remote sensing data, DEM data and meteorological data of the first area based on the combined model of Wang Zhengfei and Mao Xianmin, and determines the current forest fire spread speed of each cell in the real-time endangered range of the disaster; finally, the cellular automaton algorithm is used to process the current forest fire spread speed of each cell, and the forest fire spread prediction result of the first area in the current time period is obtained. The present application can obtain information such as combustible coefficient, slope angle and wind speed through multispectral remote sensing data, DEM data and real-time and predicted meteorological data of the forest fire occurrence area, and then accurately calculates the forest fire spread speed in each direction by using the combined model of Wang Zhengfei and Mao Xianmin, and finally simulates the forest fire spread through the cellular automaton algorithm to obtain the forest fire spread prediction result, thereby effectively solving the problems of low precision and large error of previous forest fire spread simulation, improving the scope of application of forest fire spread prediction, and providing scientific, accurate and fast guidance information for forest fire rescue, emergency disposal and post-disaster emergency material demand assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0044] Figure 1 An application scenario diagram of a forest fire spread prediction method provided in this application;

[0045] Figure 2 A flow chart of a forest fire spread prediction method provided in an embodiment of the present application;

[0046] Figure 3 Schematic diagram of a target cell, adjacent cells, and secondary adjacent cells in an embodiment of the present application;

[0047] Figure 4 This is a flow chart for calculating the current forest fire spread speed of each cell in the embodiment of the present application;

[0048] Figure 5 Another method for predicting the spread of forest fires provided in this application is a flowchart;

[0049] Figure 6 A schematic diagram of the structure of a forest fire spread prediction device provided in an embodiment of the present application;

[0050] Figure 7 A hardware structure diagram of an electronic device provided in an embodiment of the present application.

[0051] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments.

[0052] Description of reference numerals:

[0053] 101-forest fire monitoring device; 102-first data acquisition device; 103-second data acquisition device; 104-third data acquisition device; 105-processing end; 601-acquisition module; 602-calculation module; 603-prediction module; 604-display module. DETAILED DESCRIPTION

[0054] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0055] In the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference. It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or design. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way. In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more.

[0056] It should be noted that the "at..." in the embodiments of the present application can be the instant when a certain situation occurs, or can be a period of time after a certain situation occurs, and the embodiments of the present application do not specifically limit this. In addition, the forest fire spread prediction method provided in the embodiments of the present application is only used as an example, and the forest fire spread prediction method can also include more or less content.

[0057] In order to clearly describe the technical solutions of the embodiments of the present application, some terms and technologies involved in the embodiments of the present application are briefly introduced below:

[0058] Multispectral remote sensing data: It is remote sensing data obtained by synchronously imaging ground objects through sensors with two or more spectral channels. Multispectral remote sensing data will contain spectral information of multiple bands.

[0059] DEM data: DEM is the abbreviation of Digital Elevation Model, which is an important raw data for studying and analyzing terrain, watershed, and land feature identification. Since DEM data can reflect local terrain features with a certain resolution, a large amount of surface morphological information can be extracted through DEM, which can be used to draw contour lines, slope maps, aspect maps, etc.

[0060] With climate warming and more extreme weather, the danger of forest fires is also increasing. Therefore, it is of great significance to scientifically understand the mechanism and law of forest fire occurrence and development, and simulate and predict the spread of forest fires as soon as they occur, which is of great significance for fire emergency command and rescue, reducing casualties, and protecting people's lives and property safety to the greatest extent.

[0061] The current mainstream forest fire spread models include: a semi-mechanistic and semi-statistical model that focuses on the effect of slope on forest fire spread speed, the Rothermel model based on the law of conservation of energy, the McArthur model based on statistics, and China's Wang Zhengfei model.

[0062] However, most of the current forest fire spread model predictions use a single model, such as only using algorithms such as cellular automata to simulate the spread of forest fires, without actually calculating the speed, intensity and other physical states of the forest fire spread, or only using a single Wang Zhengfei model combined with relevant geographical factors to calculate the speed of forest fire spread and then use simple rules to deduce the situation of forest fire spread. This single model has low prediction accuracy and cannot adapt to the complex actual geographical environment, making it difficult to provide accurate guidance information for forest fire rescue and emergency response; and the Wang Zhengfei forest fire spread model cannot adapt to the complex actual geographical environment. The model does not consider the impact of combustible humidity on the forest fire spread speed, does not perform detailed classification calculations on the correction coefficients of different types of combustibles, and does not fully consider the impact of different slopes on the forest fire spread speed. This model has errors in the calculation of forest fire spread speed and limitations that cannot be widely applied.

[0063] In order to solve the above problems, the present application provides a forest fire spread prediction method, device, equipment and storage medium, wherein the forest fire spread prediction method is based on multispectral remote sensing data, DEM data and meteorological data using the Wang Zhengfei and Mao Xianmin combined model and cellular automaton algorithm to simulate and predict the spread of forest fires. The use of multispectral remote sensing data can provide more parameters such as vegetation type and other information for model prediction. Combined with the Wang Zhengfei and Mao Xianmin combined model, it can effectively overcome the shortcomings of large forest fire spread speed calculation errors and simple diffusion rules, achieve high-accuracy forest fire spread prediction effects, output key disaster warning information such as forest fire disaster intensity, high-risk areas, and forest fire arrival time at different locations, and provide scientific, accurate and rapid guidance information for forest fire rescue, emergency response and post-disaster emergency material demand assessment.

[0064] Figure 1 A diagram of an application scenario of a forest fire spread prediction method provided in the present application. The application scenario includes: a forest fire monitoring device 101, a first data acquisition device 102, a second data acquisition device 103, a third data acquisition device 104, and a processing end 105. When the forest fire monitoring device 101 detects that a forest fire disaster has occurred in the current area or is in a forest fire disaster state, it regularly sends an early warning signal and the location information of the disaster site to the processing end. After the processing end receives the early warning signal and the location information of the disaster site, it obtains the real-time multispectral remote sensing data of the corresponding area from the first data acquisition device 102, obtains the DEM data of the corresponding area from the second data acquisition device 103, and obtains the real-time and future predicted meteorological data of the corresponding area from the third data acquisition device 104. The processing end can obtain the forest fire spread prediction result of the corresponding area by processing the multispectral remote sensing data, DEM data, and meteorological data. In the process of forest fire disaster, the processing end 105 obtains the latest multispectral remote sensing data, DEM data, and meteorological data, so as to update the prediction of forest fire spread in real time.

[0065] In the present application, the forest fire monitoring device 101 can comprehensively determine whether to issue forest fire disaster warning information based on multiple factors such as meteorological conditions, geographical location, temperature, etc.

[0066] The first data collection device 102 can collect multi-spectral remote sensing data of the disaster site through remote sensing satellites, aircraft and drones. The remote sensing satellites can be open source and free, or commercial.

[0067] The second data acquisition device 103 can directly obtain data from the existing officially drawn DEM data.

[0068] The third data collection device 104 can directly obtain real-time and future predicted meteorological data from the local climate data center.

[0069] The processing end 105 may be a mobile terminal such as a smart phone or a tablet computer, or may be a device such as a desktop computer or a server.

[0070] Figure 2 A flow chart of a forest fire spread prediction method provided in an embodiment of the present application. Figure 2 As shown, the above-mentioned forest fire spread prediction method includes:

[0071] S210: In response to a signal of a disaster, multispectral remote sensing data, DEM data, and meteorological data of a first area in a current time period are obtained, the first area being larger than a second area, and the second area being a final endangered area inferred according to a real-time endangered area of ​​the disaster;

[0072] When a forest fire disaster occurs, the first thing to do is to determine the real-time endangered scope of the disaster. The so-called real-time endangered scope of the disaster is the geographical scope (such as longitude and latitude range or radius range) affected by the forest fire after receiving the warning signal, not the actual burning scope of the forest fire. It should be noted that the real-time endangered scope of the disaster can be the initial geographical scope affected by the forest fire when the disaster just occurs, or the real-time geographical scope at any time after the disaster occurs (while still in the disaster).

[0073] Then, based on the real-time endangered scope of the disaster, combined with local terrain information, combustible properties, soil geological information and future weather information, the final endangered scope that may be affected by future forest fire disasters, that is, the second area, is inferred. Similarly, the final endangered scope here is also a geographical scope, not the actual coverage of the fire.

[0074] After the second area is determined, it is necessary to select a suitable first area. The first area is a geographical range that is obviously larger than the second area, which plays a role in determining the approximate range where forest fire disasters may occur. For example, the first area can be selected as a 20 km × 20 km longitude and latitude range, or a 20 km circle with the second area as the center, or a longitude and latitude range where the town or county-level administrative area of ​​the second area is located.

[0075] If the second area is not easy to determine, a geographical area that is much larger than the real-time hazard range of the disaster may be directly selected as the first area.

[0076] During the disaster, when the real-time scope of the disaster changes, the scope of the second area changes at any time due to other factors. Therefore, in order to avoid the first area from changing at any time, it is generally selected to have a geographical scope that is significantly larger than the second area.

[0077] For example, the real-time endangered area when a forest fire disaster occurs, and the longitude and latitude ranges of the first area and the second area can be obtained from the local management department of the disaster-occurring area.

[0078] After obtaining the geographic scope of the first area (such as longitude and latitude), it is necessary to obtain multispectral remote sensing data, DEM data and meteorological data of the first area. Since the first area is much larger than the second area, under normal circumstances, the size of the first area will not be affected by the real-time endangered area of ​​the disaster or the second area (the final endangered area) that changes due to the real-time endangered area of ​​the disaster.

[0079] S220: Based on the combined model of Wang Zhengfei and Mao Xianmin, the multispectral remote sensing data, DEM data and meteorological data of the first region are processed to determine the current forest fire spreading speed of each cell of the real-time endangered range of the disaster, where the cell is the region obtained by dividing the first region;

[0080] In this step, the multispectral remote sensing data, DEM data and meteorological data obtained in step S210 are preprocessed and processed through the combined model of Wang Zhengfei and Mao Xianmin to obtain the current forest fire spread speed of each cell in the real-time disaster-affected range. The cells here are preferably the grid areas obtained by dividing the first area.

[0081] Figure 3 Schematic diagram of the target cell, adjacent cells, and secondary adjacent cells in the embodiment of the present application. Figure 3 As shown, each central cell has four adjacent neighbor cells above, below, left, and right, and four diagonal neighbor cells.

[0082] In a specific implementation, the multispectral remote sensing data, DEM data and meteorological data of the first area are processed based on the combined model of Wang Zhengfei and Mao Xianmin to determine the current forest fire spread speed of each cell in the real-time endangered range of the disaster, specifically including:

[0083] S221: preprocessing the multispectral remote sensing data, DEM data and meteorological data of the first area to obtain the multispectral remote sensing data, DEM data and meteorological data of the second area;

[0084] Specifically, this step is to clip the multispectral remote sensing data, DEM data and meteorological data of the first area, such as by intercepting part of the data through ArcGIS software, so as to obtain only the multispectral remote sensing data, DEM data and meteorological data of the second area which is smaller than the first area. This can reduce the amount of data for subsequent simulation calculations, thereby improving processing efficiency.

[0085] S222: determining a combustible material coefficient, a slope angle, and a wind speed according to the multispectral remote sensing data, the DEM data, and the meteorological data of the second area;

[0086] Specifically, the combustible coefficient of the corresponding area is obtained through the multispectral remote sensing data of the second area, and the slope angle information of the corresponding area is obtained through the DEM data of the second area. The slope angle here is a vector, that is, in addition to the size, it also has an inclination direction. The wind speed, temperature and other information of the corresponding area are obtained through the meteorological data of the second area. The wind speed here is also a vector, which has wind direction in addition to the size of the wind speed.

[0087] In one embodiment, the calculation method of the combustible coefficient of the second region includes:

[0088] Determine a normalized vegetation index based on multispectral remote sensing data of the second area; determine different vegetation types in non-vegetated areas and vegetation areas of the second area based on the normalized vegetation index; and determine a combustible coefficient of the second area based on a combustible coefficient table of different vegetation types.

[0089] Multispectral remote sensing data contains reflectance values ​​of different bands. The Normalized Difference Vegetation Index (NDVI) is a remote sensing indicator that reflects the land cover vegetation status. It is defined as the quotient of the difference between the reflectance of the near-infrared channel and the visible light channel and their sum. In multispectral remote sensing data, it is the difference between the reflectance value of the near-infrared band NIR and the reflectance value of the red light band R divided by the sum of the above two, as follows:

[0090]

[0091] By calculating the normalized vegetation index values ​​at different points in the second area, the non-vegetation area and the vegetation area with different vegetation types in the second area are determined according to different thresholds. Since different vegetation types have different combustible coefficients, the corresponding combustible coefficient information can be obtained according to the vegetation area in the second area.

[0092] During the specific implementation process, the range of the second area where the normalized vegetation index does not exceed 0.1 is regarded as a non-vegetation area and is assigned a non-flammable state.

[0093] By calculating the normalized vegetation index, we can obtain vegetation type information at the disaster site based on the satellite's multispectral remote sensing data, enrich the calculation data for subsequent forest fire spread speed, and improve the accuracy of forest fire spread prediction.

[0094] In addition to the above methods for calculating the fuel coefficient, other vegetation index calculation methods can also be used, such as the Enhanced Vegetation Index (EVI) and the Soil Adjusted Vegetation Index (SAVI) to distinguish different vegetation types.

[0095] Through steps S221 and S222, the parameters required for forest fire spread prediction can be obtained.

[0096] S223: The combustible coefficient, slope angle and wind speed of the second area are processed using the combined model of Wang Zhengfei and Mao Xianmin to obtain the current forest fire spread speed of each cell in the real-time endangered range of the disaster.

[0097] In this step, the combustible coefficient, slope angle and wind speed of the second area calculated in the previous steps are substituted into the combined model of Wang Zhengfei and Mao Xianmin, so that the current forest fire spread speed of each cell in the real-time disaster-affected range at different times can be obtained, thereby preparing for subsequent forest fire predictions.

[0098] S230: Using a cellular automation algorithm to process the current forest fire spread speed of each cell, and obtaining a forest fire spread prediction result for the first area in the current time period.

[0099] According to the forest fire spread speed at different times and in different cells obtained in step S223, the model prediction duration and iteration step are set based on the forest fire diffusion rules of cellular automata to obtain the forest fire spread range and area under the specified simulation duration, and output key disaster warning information such as the intensity of forest fire disasters, high-risk areas, and forest fire arrival time at different locations.

[0100] The above-mentioned embodiment can obtain information such as combustible coefficient, slope angle and wind speed through multi-spectral remote sensing data, DEM data and real-time and predicted meteorological data in the forest fire occurrence area, and then use the combined model of Wang Zhengfei and Mao Xianmin to accurately calculate the forest fire spread speed in all directions. Finally, the forest fire spread is simulated through the cellular automaton algorithm to obtain the forest fire spread prediction result, thereby effectively solving the problems of low accuracy and large error in previous forest fire spread simulations, and improving the scope of application of forest fire spread predictions. It can provide scientific, accurate and fast guidance information for forest fire rescue, emergency disposal, and post-disaster emergency material demand assessment.

[0101] Figure 4 This is a flow chart for calculating the current forest fire spread speed of each cell in the embodiment of this application. Figure 2 Based on the embodiment shown, the forest fire spread prediction method is specifically described. Figure 4 As shown in the figure, in the forest fire spread prediction method, the combustible coefficient, slope angle and wind speed of the second area are processed by the combined model of Wang Zhengfei and Mao Xianmin to obtain the current forest fire spread speed of each cell in the real-time endangered range of the disaster, including:

[0102] S410: Determine a combustible material configuration pattern coefficient according to a combustible material coefficient of the second region;

[0103] The combustible material configuration pattern coefficient is used to characterize the flammability of combustibles and whether the configuration pattern is conducive to combustion. The combustible material configuration pattern coefficient can be specified as a constant or can be classified according to Table 1.

[0104] Table 1 Combustible configuration pattern coefficients for different combustible types

[0105]

[0106] S420: determining a wind action coefficient according to the angle between the wind speed direction in the second area and the forest fire spreading direction and the wind speed;

[0107] As we all know, within a certain range, the greater the wind speed, the greater the spreading speed in the wind direction, that is, the greater the wind action coefficient, which means the greater the spreading speed gain caused by the wind speed.

[0108] Specifically, the wind action coefficient satisfies:

[0109] K ω =e 0.1788Vcosθ

[0110] Among them, V is the wind speed, θ is the angle between the wind speed direction and the forest fire spread direction. When θ=0, the forest fire spread direction is the wind speed direction.

[0111] S430: determining a slope adjustment coefficient according to the slope angle and the angle between the slope direction and the forest fire spreading direction;

[0112] Slope adjustment factor satisfy:

[0113]

[0114] in, is the slope angle, and φ is the angle between the slope direction and the direction of forest fire spread.

[0115] It should be noted that the processing of steps S410, S420, and S430 can be performed in an interchangeable order or simultaneously.

[0116] S430: Determine the current forest fire spreading speed of each cell in different forest fire spreading directions.

[0117] The calculation formula for the current forest fire spread speed of each cell in different forest fire spread directions is:

[0118]

[0119] Among them, R0 is the initial spreading speed in the absence of wind, which satisfies:

[0120] R0=aT+bV+ch-D

[0121] T is the maximum temperature of the day, W is the average wind level at noon, h is the daily hourly humidity, a, b, c, and D are constants, for example: a=0.03, b=0.05, c=0.01, and D=0.3.

[0122] Combining the above analysis, we can get the current forest fire spread speed in different forest fire spread directions as follows:

[0123]

[0124] by Figure 3 For example, assuming that the angle between the wind speed direction and the forest fire spread direction OH is θ, then the wind action coefficient of the central cell in the directions of OA, OB, OC, OD, OE, OF, and OG is e 0.1788Vcos(θ-k·45°) , where k = 1, 2,...7.

[0125] In this way, we can get the component velocities of the central cell in the directions of the four adjacent cells and the four secondary adjacent cells. Take the component velocities of the adjacent cell (i, j+1) in the OB direction and the secondary adjacent cell (i-1, j+1) in the OA direction as an example:

[0126] The velocity component of the central cell in the OB direction is:

[0127]

[0128] The velocity component of the central cell in the OA direction is:

[0129]

[0130] Figure 5 Another method for predicting the spread of forest fires provided in this embodiment is a flow chart. Figure 2 Based on the embodiment shown, the forest fire spread prediction method is specifically described. Figure 5 As shown, the above-mentioned forest fire spread prediction method includes:

[0131] S510: In response to a signal of a disaster, multispectral remote sensing data, DEM data, and meteorological data of a first area in a current time period are obtained, the first area being larger than a second area, and the second area being a final endangered area estimated based on the real-time endangered area of ​​the disaster;

[0132] The details of this step are the same as those of S210 and will not be repeated here.

[0133] It should be noted that multispectral remote sensing data can be obtained from open source free or commercial websites. In this embodiment, multispectral remote sensing data is obtained from data taken by the Landsat-5 satellite. The specific acquisition method is: register and log in to the United States Geological Survey, select the latitude and longitude range, product category, cloud coverage, time range and other parameters required for the research, and obtain the corresponding satellite remote sensing image data.

[0134] The Landsat-5 satellite is the optical remote sensing satellite with the longest operating time in orbit, and it collects the most extensive multispectral remote sensing data. This embodiment uses its data to calculate the normalized vegetation index, thereby obtaining vegetation type information.

[0135] In addition, multispectral remote sensing data can also be used to calculate the normalized vegetation index using remote sensing image data from the Gaofen series of satellites and the Sentinel series of satellites.

[0136] The DEM data of this embodiment can come from the surveying and mapping data of the United States Geological Survey (USGS) to calculate the slope angle information of the disaster-occurring area. The DEM data of China's geospatial data cloud platform can also be used.

[0137] The meteorological data of this embodiment can be downloaded from the China Meteorological Data Network.

[0138] S520: Based on the combined model of Wang Zhengfei and Mao Xianmin, the multispectral remote sensing data, DEM data and meteorological data of the first region are processed to determine the current forest fire spreading speed of each cell of the real-time endangered range of the disaster, where the cell is the region obtained by dividing the first region;

[0139] The details of this step are the same as those of S220 and will not be repeated here.

[0140] It should be noted that the cells of this embodiment may be selected in a grid range of 30m×30m.

[0141] S530: Obtain the combustion state of the target cell in the current time period;

[0142] The target cell can be any one of the cells in the first area. During the spread of forest fire, the burning state of the cell at time t is defined as:

[0143]

[0144] in, The value range is The cell goes through three states: It means that the cell has not yet burned; Indicates that the cell is in a burning state; It means that the cell has been completely burned. Only completely burned cells can ignite adjacent cells.

[0145] S540: Determine the burning state of the target cell in the next time period according to the burning state of the target cell in the current time period, the current forest fire spreading speed of the target cell, the current forest fire spreading speed of the adjacent cells adjacent to the target cell, and the current forest fire spreading speed of the next adjacent cells adjacent to the target cell;

[0146] After obtaining the current forest fire spread speed of each cell, the burning state of the target cell in the next time period can be determined based on the burning state of the target cell in the current time period, the current forest fire spread speed of the target cell, the current forest fire spread speed of the adjacent cells adjacent to the target cell, and the current forest fire spread speed of the secondary adjacent cells adjacent to the target cell.

[0147] In a specific embodiment, the combustion state of the target cell in the next time period is calculated as follows:

[0148]

[0149] Among them, t is the current time period, Δt is the time step of a spread, is the combustion state of the target cell in the current time period, is the combustion state of the target cell in the next time period, is the current forest fire spread speed of the four adjacent cells of the target cell, is the current forest fire spread speed of the four secondary adjacent cells of the target cell, a is the side length of the cell, i is the horizontal coordinate of the target cell, and j is the vertical coordinate of the target cell.

[0150] In some embodiments, the combustion state of the target cell in the next time period is determined only by the combustion states of the four adjacent cells. In this embodiment, the combustion state of the target cell in the next time period is determined based on the combustion states of the four adjacent cells and the four sub-adjacent cells, which can improve the prediction accuracy of the combustion state of each cell and correspondingly improve the prediction accuracy of forest fire spread.

[0151] The time step Δt of forest fire spread can be determined as follows:

[0152]

[0153] Among them, m is the correction coefficient, which can be taken as 0.125 according to experience, R max It is the maximum value among the current forest fire spread speed of the target cell and the current forest fire spread speed of the adjacent cells and the secondary adjacent cells.

[0154] S550: Obtaining a forest fire spread prediction result for the first area in the current time period according to the combustion state of each target cell in the next time period;

[0155] After the combustion status of each target cell in the first area at the next moment is obtained, the forest fire spread prediction result of the first area in the current time period can be determined based on it.

[0156] After the above steps, it also includes:

[0157] S560: synthesizing the multispectral remote sensing data of different bands of the first region to obtain an image of the first region, and applying the forest fire spread prediction result of the first region to the image of the first region to display the burned area.

[0158] Multi-band synthesis of multispectral remote sensing data collected by Landsat satellites can be achieved through ArcGIS software.

[0159] Through the above steps, the relative position of the burned area can be clearly displayed on the map to verify the forest fire spread prediction results. It can also facilitate the staff to directly observe the fire spread trend and provide more intuitive guidance information for forest fire rescue, emergency response, and post-disaster emergency material demand assessment.

[0160] Figure 6 A schematic diagram of the structure of a forest fire spread prediction device provided in an embodiment of the present application, the device may be in the form of software and / or hardware, and the forest fire spread prediction device includes:

[0161] The acquisition module 601 is used to respond to the signal of the disaster occurrence and acquire the multispectral remote sensing data, DEM data and meteorological data of the first area in the current time period, the first area is larger than the second area, and the second area is the final endangered area estimated according to the real-time endangered area of ​​the disaster;

[0162] A calculation module 602 is used to process the multispectral remote sensing data, DEM data and meteorological data of the first region based on the Wang Zhengfei and Mao Xianmin combined model to determine the current forest fire spread speed of each cell of the real-time endangered range of the disaster, where the cell is the region obtained by dividing the first region;

[0163] The prediction module 603 is used to process the current forest fire spread speed of each cell using a cellular automation algorithm to obtain a forest fire spread prediction result for the first area in the current time period.

[0164] The calculation module 602 is specifically configured as follows:

[0165] Preprocessing the multispectral remote sensing data, DEM data and meteorological data of the first area to obtain the multispectral remote sensing data, DEM data and meteorological data of the second area;

[0166] Determine the combustible factor, slope angle, and wind speed based on multispectral remote sensing data, DEM data, and meteorological data of the second region;

[0167] The combined model of Wang Zhengfei and Mao Xianmin was used to process the combustible coefficient, slope angle and wind speed in the second area to obtain the current forest fire spread speed of each cell in the real-time endangered range of the disaster.

[0168] In the calculation module 602, the combustible coefficient of the second region is calculated as follows:

[0169] determining a normalized difference vegetation index based on multispectral remote sensing data of a second region;

[0170] determining non-vegetated areas and different vegetation types in the vegetation areas of the second region according to the normalized difference vegetation index;

[0171] The combustible material coefficient of the second area is determined according to the combustible material coefficient table of different vegetation types.

[0172] In the calculation module 602, the combustible coefficient, slope angle and wind speed of the second area are processed using the Wang Zhengfei and Mao Xianmin combined model to obtain the current forest fire spread speed of each cell in the real-time endangered range of the disaster, specifically including:

[0173] Determining the combustible material configuration pattern coefficient according to the combustible material coefficient of the second area;

[0174] The wind action coefficient is determined according to the angle between the wind speed direction in the second area and the direction of forest fire spread and the wind speed;

[0175] For each cell, determine the current forest fire spread speed in different forest fire spread directions.

[0176] The prediction module 603 is specifically configured as follows:

[0177] Get the combustion status of the target cell in the current time period;

[0178] Determine the burning state of the target cell in the next time period according to the burning state of the target cell in the current time period, the current forest fire spreading speed of the target cell, the current forest fire spreading speed of the adjacent cells adjacent to the target cell, and the current forest fire spreading speed of the next adjacent cells adjacent to the target cell;

[0179] According to the burning status of each target cell in the next time period, the forest fire spread prediction result of the first area in the current time period is obtained.

[0180] In the prediction module 603, the specific calculation formula for the combustion state of the target cell in the next time period is:

[0181]

[0182] Among them, t is the current time period, Δt is the time step of a spread, is the combustion state of the target cell in the current time period, is the combustion state of the target cell in the next time period, is the current forest fire spread speed of the four adjacent cells located in the east, south, west, north, or above, below, left, and right of the target cell. is the current forest fire spread speed of the four secondary adjacent cells located in the southwest, northwest, southeast, northeast or diagonal of the target cell, a is the side length of the cell, i is the horizontal coordinate of the target cell, and j is the vertical coordinate of the target cell.

[0183] After the prediction module 603, a display module 604 is also included, which is configured to:

[0184] Synthesizing multispectral remote sensing data of different bands of the first region to obtain an image of the first region;

[0185] The forest fire spread prediction result of the first area is applied to the first area image to display the burned area.

[0186] The forest fire spread prediction device provided in the embodiment of the present application has the same implementation principle and technical effects as those in the aforementioned forest fire spread prediction method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned forest fire spread prediction method embodiment.

[0187] Figure 7 This is a hardware structure diagram of an electronic device provided in an embodiment of the present application. The embodiment provides an electronic device, including: a processor 701, and a memory 702 communicatively connected to the processor 701; the memory 702 stores computer execution instructions; the processor 701 executes the computer execution instructions stored in the memory 702 to implement the description of the forest fire spread prediction method in the corresponding embodiment above.

[0188] Figure 7 The electronic device shown further includes a communication interface 703 and a communication bus 704 , wherein the processor 701 , the memory 702 and the communication interface 703 communicate with each other via the communication bus 704 .

[0189] The memory 702 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication bus 704 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of communication bus.

[0190] The communication interface 703 is used to connect to at least one user terminal and other network units through a network interface, and send the encapsulated IPv4 message or IPv4 message to the user terminal through the network interface.

[0191] The processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 701. The above processor 701 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 702, and the processor 701 reads the information in the memory 702 and completes the steps of the method of the above embodiment in combination with its hardware.

[0192] The embodiment of the present application also provides a computer storage medium, in which a computer-readable storage medium stores computer-executable instructions, which are used to implement the description of the forest fire spread prediction method in the above corresponding embodiment when executed by the processor, so it will not be repeated here. In addition, the description of the beneficial effects of using the same method will not be repeated. For technical details not disclosed in the computer storage medium embodiment involved in the present invention, please refer to the description of the method embodiment of the present invention.

[0193] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the above-mentioned program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The above-mentioned storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0194] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for predicting the spread of forest fires, characterized in that: include: In response to a signal of a disaster, multispectral remote sensing data, DEM data, and meteorological data of a first area in a current time period are acquired, wherein the first area is larger than a second area, and the second area is a final endangered area estimated based on the real-time endangered area of ​​the disaster; Based on the combined model of Wang Zhengfei and Mao Xianmin, the multispectral remote sensing data, DEM data and meteorological data of the first area are processed to determine the current forest fire spread speed of each cell in the real-time endangered range of the disaster, where the cell is the area obtained by dividing the first area; The cellular automaton algorithm is used to process the current forest fire spread speed of each cell to obtain the forest fire spread prediction result of the first area in the current time period.

2. The method according to claim 1, characterized in that: The multispectral remote sensing data, DEM data and meteorological data of the first area are processed based on the combined model of Wang Zhengfei and Mao Xianmin to determine the current forest fire spread speed of each cell in the real-time endangered range of the disaster, specifically including: Preprocessing the multispectral remote sensing data, DEM data and meteorological data of the first area to obtain the multispectral remote sensing data, DEM data and meteorological data of the second area; Determine the combustible factor, slope angle, and wind speed based on multispectral remote sensing data, DEM data, and meteorological data of the second region; The combined model of Wang Zhengfei and Mao Xianmin was used to process the combustible coefficient, slope angle and wind speed in the second area to obtain the current forest fire spread speed of each cell in the real-time endangered range of the disaster.

3. The method according to claim 2, characterized in that The calculation method of the combustible coefficient of the second area includes: determining a normalized difference vegetation index based on multispectral remote sensing data of a second region; determining non-vegetated areas and different vegetation types in the vegetation areas of the second region according to the normalized difference vegetation index; The combustible material coefficient of the second area is determined according to the combustible material coefficient table of different vegetation types.

4. The method according to claim 2 or 3, characterized in that: The Wang Zhengfei and Mao Xianmin combined model is used to process the combustible coefficient, slope angle and wind speed of the second area to obtain the current forest fire spread speed of each cell in the real-time endangered range of the disaster, including: Determining the combustible material configuration pattern coefficient according to the combustible material coefficient of the second area; The wind action coefficient is determined according to the angle between the wind speed direction in the second area and the direction of forest fire spread and the wind speed; The slope adjustment coefficient is determined based on the slope angle and the angle between the slope direction and the direction of forest fire spread; Determine the current forest fire spread speed for each cell in different forest fire spread directions.

5. The method according to claim 1, characterized in that The method of using the cellular automaton algorithm to process the current forest fire spread speed of each cell to obtain the forest fire spread prediction result of the first area in the current time period includes: Get the combustion status of the target cell in the current time period; Determine the burning state of the target cell in the next time period according to the burning state of the target cell in the current time period, the current forest fire spreading speed of the target cell, the current forest fire spreading speed of the adjacent cells adjacent to the target cell, and the current forest fire spreading speed of the next adjacent cells adjacent to the target cell; According to the combustion status of each of the target cells in the next time period, a forest fire spread prediction result of the first area in the current time period is obtained.

6. The method according to claim 5, characterized in that The determining the burning state of the target cell in the next time period according to the burning state of the target cell in the current time period, the current forest fire spreading speed of the target cell, the current forest fire spreading speed of the adjacent cells adjacent to the target cell, and the current forest fire spreading speed of the secondary adjacent cells adjacent to the target cell specifically includes: The combustion state of the target cell in the next time period is determined by the following formula: Among them, t is the current time period, Δt is the time step of a spread, is the combustion state of the target cell in the current time period, is the combustion state of the target cell in the next time period, is the current forest fire spreading speed of the four adjacent cells of the target cell, is the current forest fire spread speed of the four secondary adjacent cells of the target cell, a is the side length of the cell, i is the horizontal coordinate of the target cell, and j is the vertical coordinate of the target cell.

7. The method according to claim 1, characterized in that After the cellular automaton algorithm is used to process the current forest fire spread speed of each cell to obtain the forest fire spread prediction result of the first area in the current time period, the method further includes: Synthesizing multispectral remote sensing data of different bands of the first region to obtain an image of the first region; The forest fire spread prediction result of the first area is applied to the first area image to display the burned area.

8. A forest fire spread prediction device, comprising: An acquisition module, configured to respond to a signal of a disaster occurrence and acquire multispectral remote sensing data, DEM data, and meteorological data of a first area in a current time period, wherein the first area is larger than a second area, and the second area is a final endangered area inferred according to a real-time endangered area of ​​the disaster; A calculation module, for processing the multispectral remote sensing data, DEM data and meteorological data of the first region based on the Wang Zhengfei and Mao Xianmin combined model, and determining the current forest fire spread speed of each cell of the real-time endangered range of the disaster, wherein the cell is a region obtained by dividing the first region; The prediction module is used to process the current forest fire spread speed of each cell using a cellular automaton model to obtain the forest fire spread prediction result of the first area in the current time period.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images