A downscaling prediction method and system for local wind fields of forest fires considering fire-atmosphere interaction

Abstract

The present invention provides a method and system for downscaling prediction of local wind fields in forest fires that considers fire-atmosphere interaction. The method comprises: obtaining time series data of meteorological attributes at different locations of the fire scene, the spatial location of each meteorological station, and time series data of infrared images of the fire spread process observed by remote sensing; approximately determining the direction of the fire head, and then determining the direction of the fire tail and both flanks; determining meteorological data near the fire head, the fire tail, and the fire flanks; extracting time series data of descriptive indicators of the fire spread situation through infrared image data of the fire spread process; establishing a deep learning model to train a four-directional wind speed and direction prediction model for the local forest fire; and estimating the wind speed and direction at each location within the fire scene based on the output data of the four-directional wind speed and direction prediction model of the fire scene through interpolation to achieve wind field downscaling.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent prevention and control of forest fires, and specifically provides a downscaling prediction method and system for local wind fields of forest fires taking into account fire-atmosphere interaction. Background Art

[0002] In recent years, global warming and the frequent occurrence of extreme weather have led to an increasing frequency of forest fires. Therefore, to reduce the human toll of wildfires, the development of intelligent forest fire prevention and control tools and systems is imperative. Wind plays a crucial role in forest fires, influencing their origin, spread, and control, making them more destructive and dangerous. Therefore, understanding and monitoring wind speed and direction are crucial for effective fire management and control during fire prevention and response. However, during fire development, the spread of fires and wind patterns interact in complex ways. For example, large-scale fires generate strong thermals, which rise and form convection currents, causing dramatic changes in wind speed and direction. Strong winds draw fresh air into the fire zone, increasing the oxygen supply, fueling flames, and intensifying the intensity of the fire. Therefore, to estimate the wind pattern at the local fire site, it is necessary to consider the impact of the fire spread on the wind pattern and conduct in-depth research on fire-atmosphere interactions.

[0003] Wind speed and direction forecasting has attracted widespread attention across multiple fields. Artificial intelligence-based forecasting methods are gaining increasing attention and becoming one of the most effective. These methods primarily exploit time-varying trends in wind speed or direction from historical wind speed data to predict future wind speeds. However, due to disturbances caused by fire-atmosphere interactions, these methods are often ineffective for downscaling wind predictions within the local fire zone. The key issue is their inability to fully utilize fire spread data to support local wind modeling. Summary of the Invention

[0004] To address the difficulties mentioned in the background technology, the present invention aims to provide a method and system for downscaling local wind prediction at a fire site, integrating fire spread data and historical meteorological data as input. This method expands the dimensionality of the wind speed and direction prediction model inputs; establishes a multivariate time series deep learning model; and predicts wind speed and direction values ​​at key locations within the fire site based on historical meteorological data and descriptive indicators of fire spread. Furthermore, wind vectors at various locations within the fire site are interpolated from the four-dimensional wind speed and direction values. This provides data support for forest fire prevention and control decisions.

[0005] In order to achieve the above object, the technical solution adopted in the present invention is:

[0006] A downscaling prediction method for local wind fields of forest fires considering fire-atmosphere interaction includes the following steps:

[0007] Step 1: Obtain the time series data of meteorological attributes at different locations of the fire scene, the spatial location of each meteorological station, and the time series data of infrared images of the fire spread process observed by remote sensing.

[0008] Step 2: Based on the direction of change in the temperature center of gravity during the fire spread process, approximately determine the direction of the fire head, and then determine the direction of the fire tail and both wings.

[0009] Step 3: Calculate the distance between the location of each weather station in step 1 and the straight lines in the four directions in step 2, and select the monitoring data of the weather station with the shortest distance to each straight line as the weather data near the fire head, the weather data near the fire tail, and the weather data near the two wings.

[0010] Step 4: Extract the time series data of fire spread situation descriptive indicators through the infrared image data of the fire spread process.

[0011] Step 5: Based on the time series data of meteorological attributes of the four directions of the fire scene obtained in step 3 and the time series data of descriptive indicators of the fire spread situation obtained in step 4, the final data set is established.

[0012] Step 6: Establish a deep learning model and train a four-dimensional wind speed and direction prediction model for the local forest fire based on the time series dataset described in Step 5.

[0013] Step 7: Using the Kriging interpolation method, based on the output data of the four-azimuth wind speed and direction prediction model of the fire scene, the wind speed and direction at each location within the fire scene are estimated, and the wind field is ultimately downscaled.

[0014] Furthermore, the meteorological attributes described in step 1 include wind speed, wind direction, temperature, humidity, and air pressure; the meteorological stations described in step 1 should be evenly distributed around the fire scene, and the number of meteorological stations N>=4; the infrared image pixel value described in step 1 is equal to the temperature of the pixel point.

[0015] Furthermore, in step 2, the direction of the fire head is approximately determined based on the direction of change of the temperature center of gravity during the fire spread process, and the specific process of determining the direction of the fire tail and the two wings is as follows:

[0016] Step 2.1: Binarize the infrared image using an adaptive temperature threshold. Mark the area consisting of pixels with a temperature higher than the threshold as Burned, and mark the area consisting of pixels with a temperature lower than the threshold as Unburned.

[0017] Step 2.2: Take the temperature values ​​of all pixels in the Burned area as the mass of the point and calculate the center of gravity (x, y) of the area.

[0018] Step 2.3: Assume that the center of gravity of the fire scene infrared image at time t is (xt ,y t ), the center of gravity of the fire scene infrared image at time t+1 is (x t+1 ,y t+1 ), then the direction of the fire head at time t is represented by the vector (x t+1 -x t ,y t+1 -y t ) direction; the direction of the fire tail is the opposite direction, and the directions of the two side wings form angles of 90° and 270° with the direction of the fire head respectively.

[0019] Furthermore, the fire spread situation descriptive indicators mentioned in step 4 include: the perimeter L of the burned area, the surface area S, the change in the horizontal coordinate of the center of gravity Δx, the change in the vertical coordinate Δy, the perimeter elongation r L , area expansion rate r S . r L , and r S The calculation formula is as follows:

[0020]

[0021] Where, L t+1 is the perimeter of the Burned area at time t+1; L t is the perimeter of the Burned area at time t;

[0022] S t+1 is the area of ​​the Burned region at time t+1; S t is the area of ​​the Burned region at time t.

[0023] Furthermore, the final data set described in step 5 is an M*N matrix, where M is the sum of the number of meteorological attribute variables and the descriptive indicators of the fire spread situation, and N is the number of samples, that is, the time dimension.

[0024] Furthermore, the deep learning model described in step 6 inputs the four-direction meteorological attribute data of the fire scene and the descriptive indicator data of the fire spread situation at the previous n moments, and outputs the four-direction wind speed and direction values ​​at the n+1th moment.

[0025] Furthermore, the deep learning model described in step 6 includes but is not limited to a CNN-LSTM model.

[0026] A downscaling prediction system for local wind fields due to forest fires that considers fire-atmosphere interactions includes:

[0027] The acquisition module is used to obtain the time series data of meteorological attributes at different locations of the fire scene, the spatial location data of each meteorological station, and the time series data of infrared images of the fire spread process.

[0028] The calculation module is used to calculate the descriptive index of the fire spread situation based on the infrared image data of the fire spread process.

[0029] The key location meteorological data selection module is used to determine the spread direction of the fire head, fire tail and both wings according to the changes in the temperature center of gravity during the fire spread process, and select the meteorological data near the fire head, fire tail and both wings according to the distance from the meteorological station to the straight line of each spread direction.

[0030] The prediction module is used to make predictions based on the four-directional meteorological data and fire spread situation descriptive indicator data of the previous n moments, and obtain the prediction results of the four-directional wind speed and wind direction values ​​at the n+1th moment.

[0031] The interpolation module is used to interpolate the wind speed and direction values ​​at all four directions of the fire scene at the current moment to obtain the wind speed and direction values ​​at each location in the fire scene, thereby constructing the local wind field of the fire scene.

[0032] Compared with the prior art methods, the present invention has the following beneficial effects:

[0033] The present invention provides a downscaling prediction method for local forest fire wind fields that considers fire-atmosphere interactions. This method is based on multi-directional meteorological monitoring data from the fire scene and infrared remote sensing image data of the fire spread process. The fire head, fire tail, and two wings are determined based on changes in the temperature center of gravity of the fire scene in the infrared image. Data recorded by four meteorological stations near the fire head, fire tail, and two wings are then selected as meteorological attribute inputs for the wind speed and direction prediction model. In addition, based on changes in the shape and position of the fire scene in the infrared image, indicators used to describe the fire spread situation, such as the fire perimeter and fire area, are extracted as another part of the model input. By expanding the dimensionality of the input data, the local wind speed and wind direction prediction at the fire scene not only focuses on the autocorrelation of the sequence, but also considers the fire-atmosphere interaction. The method explores the impact of the fire scene status on the wind vector and extracts descriptive indicators of the fire spread situation to support wind vector modeling, providing a new solution for local wind vector prediction at the fire scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a flow chart of a downscaling prediction method for local wind fields of forest fires taking into account fire-atmosphere interaction according to the present invention;

[0035] Figure 2 This is a schematic diagram showing the calculation principle of the fire head direction at consecutive moments in a fire scene according to an embodiment of the present invention;

[0036] Figure 3 This is a structural diagram of a deep learning model in an embodiment of the present invention;

[0037] Figure 4 This is a diagram showing the interpolation results of the local wind speed at the fire scene in an embodiment of the present invention;

[0038] Figure 5 This is a diagram showing the interpolation results of the local wind direction at a fire scene in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments:

[0040] Combine Figure 1 The first object of the present invention is to provide a downscaling prediction method for local wind fields of forest fires considering fire-atmosphere interaction, which specifically comprises the following steps:

[0041] Step 1: Obtain the time series data of meteorological attributes at different locations of the fire scene, including wind speed, wind direction, temperature, humidity, and air pressure; the location of each meteorological station, and the time series data of infrared images of the fire spread process observed by remote sensing, and establish the initial dataset M. Its data structure is shown in Table 1:

[0042] Table 1

[0043]

[0044] Step 2: Based on the temperature corresponding to each pixel value of the fire scene infrared image, calculate the center of gravity coordinates of the current burning infrared image, combined with Figure 2 The directions of the fire head, fire tail and two wings are determined according to the vector formed by the temperature center of the remote sensing image at the current moment and the temperature center of the remote sensing image at the next moment.

[0045] 2.1) Binarize the infrared image using an adaptive temperature threshold, marking the area consisting of pixels with a temperature higher than the threshold as burned, and the area consisting of pixels with a temperature lower than the threshold as unburned;

[0046] 2.2) Treat the temperature values ​​of all pixels in the burned area as the mass of the point and calculate the center of gravity (x, y) of the area;

[0047] 2.3) Let the center of gravity of the infrared image of the fire scene at time t be (x t ,y t ), the center of gravity of the fire scene infrared image at time t+1 is (x t+1 ,y t+1 ), then the direction of the fire head at time t is represented by the vector (x t+1 -x t ,y t+1 -y t ) direction; the direction of the fire tail is the opposite direction, and the directions of the two side wings form angles of 90° and 270° with the direction of the fire head respectively.

[0048] Step 3: Calculate the distance between the current position of each meteorological station and the straight lines of the fire head, fire tail, and both wings, and select the meteorological data collected by the meteorological station closest to each straight line as the meteorological attributes near the fire head, near the fire tail, near the left wing, and near the right wing.

[0049] Step 4: Using image processing technology, calculate the following fire spread situation descriptive indicators corresponding to each moment based on the infrared remote sensing image of the fire spread process: Burned area perimeter L, surface area S, center of gravity horizontal coordinate change Δx, vertical coordinate change Δy, perimeter elongation r L , area expansion rate r S . r L , and r S The calculation formula is as follows:

[0050]

[0051] Where, L t+1 is the perimeter of the Burned area at time t+1; L t is the perimeter of the Burned area at time t;

[0052] S t+1 is the area of ​​the Burned region at time t+1; S t is the area of ​​the Burned region at time t.

[0053] Step 5: Create a final dataset based on the meteorological attribute data for the key locations (fire head, fire tail, left wing, and right wing) selected in Step 3 and the descriptive indicators of the fire spread at each moment in the spread process. The data structure of the final dataset is shown in Table 2.

[0054] Table 2

[0055]

[0056] Step 6: Establish a deep learning model. The input of the model is the meteorological attribute data of the four directions of the fire scene and the descriptive indicator data of the fire spread situation at the previous n moments, and the output is the wind speed and direction values ​​of the four directions at the n+1th moment. Based on the time series data set described in step 5, the training set and test set are set according to a certain ratio to carry out training. After completion, the wind speed and direction values ​​of the four directions of the fire scene for a certain time period in the future can be predicted. Combined with Figure 3 In this embodiment of the present invention, a CNN-LSTM model is selected as an example, but the deep learning model described in step 6 includes but is not limited to a CNN-LSTM model.

[0057] Step 7: Using the interpolation method, based on the output data of the 4-direction wind speed and direction prediction model of the fire scene, the wind speed and direction at each location inside the fire scene are estimated, and wind field downscaling is finally achieved. In the embodiment of the present invention, the Kriging interpolation method is selected, but the interpolation method described in step 7 includes but is not limited to the Kriging interpolation method. The wind speed interpolation result of the target fire scene is as follows: Figure 4 As shown in the figure, the wind direction interpolation results for the target fire scene are as follows: Figure 5 shown.

[0058] A second object of the present invention is to provide a method and system for downscaling prediction of local wind fields in forest fires taking into account fire-atmosphere interaction, comprising:

[0059] The acquisition module is used to obtain the time series data of meteorological attributes at different locations of the fire scene, the spatial location data of each meteorological station, and the time series data of infrared images of the fire spread process.

[0060] The calculation module is used to calculate the descriptive index of the fire spread situation based on the infrared image data of the fire spread process.

[0061] The key location meteorological data selection module is used to determine the spread direction of the fire head, fire tail and both wings according to the changes in the temperature center of gravity during the fire spread process, and select the meteorological data near the fire head, fire tail and both wings according to the distance from the meteorological station to the straight line of each spread direction.

[0062] The prediction module is used to make predictions based on the four-directional meteorological data and fire spread situation descriptive indicator data of the previous n moments, and obtain the prediction results of the four-directional wind speed and wind direction values ​​at the n+1th moment.

[0063] The interpolation module is used to interpolate the wind speed and direction values ​​at all four directions of the fire scene at the current moment to obtain the wind speed and direction values ​​at each location in the fire scene, thereby constructing the local wind field of the fire scene.

Claims

1. A downscaling prediction method for local wind fields of forest fires considering fire-atmosphere interaction, characterized in that: The method comprises: Step 1: Obtain time series data of meteorological attributes at different locations of the fire scene, the spatial location of each meteorological station, and time series data of infrared images of the fire spread process observed by remote sensing; Step 2: Based on the direction of change in the temperature center of gravity during the fire spread process, approximately determine the direction of the fire head, and then determine the direction of the fire tail and both wings; Step 3: Calculate the distance between the location of each weather station in step 1 and the straight lines in the four directions in step 2, and select the monitoring data of the weather station with the shortest distance to each straight line as the weather data near the fire head, the weather data near the fire tail, and the weather data near the two wings; Step 4: Extract the time series data of fire spread situation descriptive indicators through the infrared image data of the fire spread process; Step 5: Based on the time series data of meteorological attributes of the four directions of the fire scene obtained in step 3 and the time series data of descriptive indicators of the fire spread situation obtained in step 4, the final data set is established; Step 6: Build a deep learning model to train a 4-axis wind speed and direction prediction model for the local forest fire area based on the time series dataset described in Step 5. Step 7: Using the interpolation method, based on the output data of the four-direction wind speed and direction prediction model of the fire scene, the wind speed and direction at each location within the fire scene are estimated to achieve wind field downscaling; The infrared image pixel value described in step 1 is equal to the temperature of the pixel; In step 2, the temperature values ​​of all pixels in the Burned area are regarded as the mass of the point, and the center of gravity of the area is calculated; The descriptive indicators of the fire spread situation described in step 4 include: the perimeter L of the burned area, the surface area S, the change in the horizontal coordinate of the center of gravity, the change in the vertical coordinate, the perimeter elongation, and the area expansion rate.

2. The downscaling prediction method for local wind fields of forest fires considering fire-atmosphere interaction according to claim 1 is characterized in that: The meteorological attributes described in step 1 include wind speed, wind direction, temperature, humidity, and air pressure. The meteorological stations described in step 1 should be evenly distributed around the fire scene, and the number of meteorological stations N should be greater than or equal to 4. The infrared image pixel value described in step 1 is equal to the temperature of the pixel point.

3. The downscaling prediction method for local wind fields of forest fires considering fire-atmosphere interaction according to claim 2 is characterized in that: The specific steps of step 2 are: Step 2.1: Binarize the infrared image using an adaptive temperature threshold. Mark the area consisting of pixels with a temperature higher than the threshold as Burned, and the area consisting of pixels with a temperature lower than the threshold as Unburned. Step 2.2: Take the temperature values ​​of all pixels in the Burned area as the mass of the point and calculate the center of gravity (x, y) of the area; Step 2.3: Assume that the center of gravity of the fire scene infrared image at time t is (x t ,y t ), the center of gravity of the fire scene infrared image at time t+1 is (x t+1 ,y t+1 ), then the direction of the fire head at time t is represented by vector (x t+1 -x t ,y t+1 -y t ) direction; the direction of the fire tail is the opposite direction, and the directions of the two side wings form angles of 90° and 270° with the direction of the fire head respectively.

4. The downscaling prediction method for local wind fields of forest fires considering fire-atmosphere interaction according to claim 3 is characterized in that: The fire spread situation descriptive indicators mentioned in step 4 include: the perimeter L of the burned area, the surface area S, the change in the horizontal coordinate of the center of gravity Δx, the change in the vertical coordinate Δy, and the perimeter elongation r L , area expansion rate r S ; r L , and r S The calculation formula is as follows: Where, L t+1 is the perimeter of the Burned area at time t+1; L t is the perimeter of the Burned area at time t; S t+1 is the area of ​​the Burned region at time t+1; S t is the area of ​​the Burned region at time t.

5. The downscaling prediction method for local wind fields of forest fires considering fire-atmosphere interaction according to claim 4 is characterized in that: The final data set described in step 5 is an M*N matrix, where M is the sum of the number of meteorological attribute variables and the descriptive indicators of the fire spread situation, and N is the number of samples, that is, the time dimension.

6. The downscaling prediction method for local wind fields of forest fires considering fire-atmosphere interaction according to claim 5, characterized in that: The deep learning model described in step 6 inputs the four-direction meteorological attribute data of the fire scene and the descriptive indicator data of the fire spread situation at the previous n moments, and outputs the four-direction wind speed and direction values ​​at the n+1th moment.

7. The downscaling prediction method for local wind field of forest fire considering fire-atmosphere interaction according to claim 6 is characterized in that: The deep learning model described in step 6 includes but is not limited to a CNN-LSTM model; the interpolation method described in step 7 includes but is not limited to a Kriging interpolation method.

8. A downscaling prediction system for local wind fields due to forest fires considering fire-atmosphere interactions, for implementing the downscaling prediction method for local wind fields due to forest fires considering fire-atmosphere interactions as described in any one of claims 1 to 7, characterized in that: include: The acquisition module is used to obtain the time series data of meteorological attributes at different locations of the fire scene, the spatial location data of each meteorological station, and the time series data of infrared images of the fire spread process; A calculation module, used for calculating descriptive indicators of the fire spread situation based on infrared image data of the fire spread process; The key location meteorological data selection module is used to determine the spread direction of the fire head, fire tail and two wings according to the change of the temperature center of gravity during the fire spread process, and select the meteorological data near the fire head, fire tail and flanks according to the distance from the meteorological station to the straight line of each spread direction; The prediction module is used to make predictions based on the four-directional meteorological data and fire spread situation descriptive index data of the previous n moments, and obtain the prediction results of the four-directional wind speed and wind direction values ​​at the n+1th moment; The interpolation module is used to interpolate the wind speed and direction values ​​of the four directions of the fire scene at the current moment to obtain the wind speed and direction values ​​of each position in the fire scene, thereby constructing the local wind field of the fire scene.

Images