Hot spot area prediction method based on historical observation mission data

Abstract

The present invention relates to the field of remote sensing satellite control, and in particular to a hot spot area prediction method based on historical observation mission data, the method comprising obtaining the burning position and burning time of historical burning points observed by the remote sensing satellite in the target area; dividing the target area into a number of grids to be tested, and determining the number of burning points in each grid to be tested according to the burning position; determining the grid type of the grid to be tested according to the number of burning points; determining the burning situation; and selecting a prediction strategy for the hot spot area of ​​the remote sensing satellite based on the determination result. The present invention significantly improves the accuracy and pertinence of the hot spot area prediction of the remote sensing satellite by performing refined grid division and multi-dimensional analysis on the target area to predict the observed hot spot area, optimizes the satellite resource allocation, and improves the observation efficiency.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing satellite management and control, and in particular to a hotspot area prediction method based on historical observation mission data. Background Art

[0002] With the impact of global climate change and human activities, natural disasters such as forest fires and grassland fires are becoming more frequent and destructive. Timely and accurate prediction of fire hotspots has become the key to reducing disaster losses. Traditional fire prediction methods mainly rely on manual observation and ground monitoring, which have problems such as lack of real-time performance and limited coverage.

[0003] In recent years, the rapid development of remote sensing satellite technology has provided new possibilities for fire monitoring and early warning. In recent years, with the development of remote sensing technology and the improvement of satellite earth observation capabilities, remote sensing satellites can conduct continuous observations of forest conditions, but the accuracy and pertinence of observations during the observation process are relatively low.

[0004] Patent document with publication number CN115400366A discloses a method and system for handling the resurgence of forest fires based on remote sensing satellite data. The invention uses remote sensing satellites to collect detailed and accurate first data such as forest fire information and smoke information after the forest fire is first extinguished, obtains the location information of hidden fire points by processing the first data, performs on-site fire point conditions detection based on the location information of the hidden fire points, and extinguishes the hidden fire points based on the on-site fire point conditions. At the same time, for the forest after the hidden fire points are treated, remote sensing satellites are used again to obtain second data to monitor and determine the hidden fire points.

[0005] This shows the following problem: In the prior art, the use of remote sensing satellites to observe forests lacks targeted observations, resulting in low observation efficiency. Summary of the invention

[0006] To this end, the present invention provides a hot spot area prediction method based on historical observation mission data, which is used to divide the grid according to the historical burning point analysis to predict the hot spot area where the fire occurs for observation, so as to overcome the problem of low observation efficiency caused by the lack of observation targeting in the existing technology of using remote sensing satellites to observe forests.

[0007] To achieve the above object, the present invention provides a hot spot area prediction method based on historical observation task data, comprising:

[0008] Step S1, obtaining the burning position and burning time of the historical burning points observed by the remote sensing satellite in the target area;

[0009] Step S2, dividing the target area into grids according to the geographical location to form a plurality of grids to be tested, and determining the number of combustion points in each grid to be tested according to the combustion position;

[0010] Step S3, determining the grid type of the grid to be tested according to the number of the combustion points, including a first grid, a second grid and a third grid;

[0011] Step S4, determining whether there is a target adjacent grid whose grid type is the first grid among the grids adjacent to the second grid, and if there is a target adjacent grid, determining whether there is the historical burning point in the bordering part, and, if it is determined that there is a historical burning point, calculating the total vegetation bordering area of ​​the bordering part of the second grid and each target adjacent grid, calculating the vegetation bordering rate based on the total vegetation bordering area and the vegetation area of ​​the second grid, and determining whether to correct a part of the second grid to the first grid based on the vegetation bordering rate;

[0012] Step S5, calculating the combustion ratio of the target combustion point in the first grid during the dry period of the year, and comparing the combustion ratio with a preset combustion ratio threshold to determine the combustion status;

[0013] Step S6, determining whether the current weather is dry based on the current real-time temperature and real-time humidity and the corresponding preset temperature and preset humidity, predicting hot spots with a high probability of fire based on the determination result and the combustion conditions, and increasing the use of remote sensing satellites for observing the hot spots.

[0014] Furthermore, in the step S3, it includes:

[0015] Step S31, comparing the number of combustion points of each of the grids to be tested with a preset minimum number of combustion points and a preset maximum number of combustion points to obtain a comparison result;

[0016] Step S32: determining the grid type of the grid to be tested based on the comparison result.

[0017] Further, in the step S32, the process of determining the grid type of the grid to be tested based on the comparison result includes:

[0018] If the number of combustion points is greater than the maximum number of combustion points, the grid to be tested is determined as the first grid;

[0019] If the number of combustion points is less than the minimum number of combustion points, the grid to be tested is determined as the third grid.

[0020] Furthermore, in the step S4, it includes:

[0021] Step S41, determining the grid type of the adjacent grids adjacent to the four sides of the second grid;

[0022] Step S42, when there is a first grid in the adjacent grids, determining whether there is a historical burning point in the bordering part;

[0023] Step S43, when there is a historical burning point in the bordering part, obtaining the total area of ​​vegetation bordering the bordering part between the target adjacent grid and the second grid, and calculating the vegetation bordering rate;

[0024] Step S44, comparing the vegetation bordering rate with a preset standard bordering rate to obtain a comparison result, and determining whether to correct a part of the second grid to the first grid based on the comparison result.

[0025] Furthermore, in step S43, the process of calculating the vegetation bordering rate includes:

[0026] Calculating the vegetation bordering area of ​​each of the target adjacent grids and the second grid;

[0027] Calculating the sum of the bordering areas of each vegetation to obtain the total bordering area of ​​the vegetation;

[0028] The ratio of the total vegetation bordering area to the grid vegetation area of ​​the second grid is calculated to obtain the vegetation bordering rate.

[0029] Furthermore, in step S44, the process of determining whether to correct a part of the second grid to the first grid based on the comparison result includes:

[0030] If the vegetation bordering rate is greater than or equal to the standard bordering rate, determining to correct a part of the second grid into the first grid;

[0031] If the vegetation bordering rate is less than the standard bordering rate, it is determined not to correct the partial area of ​​the second grid to the first grid.

[0032] Furthermore, in step S5, the process of determining the combustion condition includes:

[0033] Determining whether the burning time of the historical burning points in the first grid is within the dry time period of the year;

[0034] Calculating a ratio of a target quantity in each of the first grids within a drying time period to the first quantity to obtain the combustion ratio;

[0035] The combustion ratio is compared with the combustion ratio threshold to obtain a comparison result, and the combustion condition is determined based on the comparison result, wherein:

[0036] If the combustion ratio is less than or equal to the combustion ratio threshold, determining that the combustion condition is non-dry combustion;

[0037] If the combustion ratio is greater than the combustion ratio threshold, the combustion condition is determined to be dry combustion. Further, in step S6, the process of predicting a hot spot area with a high probability of fire occurrence based on the determination result and the combustion condition includes:

[0038] If the current weather is dry, the hot spot area observed by the remote sensing satellite is predicted to be a dry burning area composed of the first grids where the burning conditions are dry burning;

[0039] If the current weather is not dry, the hot spot area observed by the remote sensing satellite is predicted to be a non-dry combustion area composed of the first grids where the combustion conditions are dry combustion.

[0040] Furthermore, in the step S1, the longitude and latitude coordinates of the historical burning point in the historical observation of the remote sensing satellite are obtained as the burning position, and the time when the burning occurs at the historical burning point observed by the remote sensing satellite is obtained as the burning time.

[0041] Furthermore, in the step S2, it includes:

[0042] Step S21, dividing the target area into a plurality of grids to be measured of equal size at equal intervals according to the geographical location according to the preset grid division accuracy;

[0043] Step S22, marking each of the historical combustion points in the grid to be tested according to the combustion position;

[0044] Step S23, obtaining the number of the historical combustion points in each of the grids to be tested to obtain the number of combustion points.

[0045] Compared with the prior art, the beneficial effect of the present invention lies in that, by performing refined grid division and multi-dimensional analysis on the target area to predict the hot spot area for observation, the accuracy and pertinence of the hot spot area prediction of the remote sensing satellite are significantly improved. Through the historical burning point data, the target area is divided into different types of grids, and the grids are dynamically adjusted according to the distribution characteristics of the burning points in the grids. The vegetation border rate is evaluated according to the regional geographical environment characteristics, which can more accurately identify potential high-risk areas and improve the prediction accuracy. By analyzing the time distribution of the burning points in the first grid and combining the current weather conditions, the burning situation can be intelligently distinguished, and the accuracy of the hot spot area prediction can be greatly improved. This method can not only dynamically adjust the observation strategy of the remote sensing satellite, but also optimize the satellite resource allocation, significantly improving the observation efficiency and early warning capability.

[0046] Furthermore, by strictly comparing the number of burning points in each grid with the preset minimum and maximum number of burning points, a systematic and quantitative classification of grid types is achieved, which can objectively reflect the degree of fire risk in different grid areas, provide a more accurate data basis for subsequent hot spot area predictions, and significantly improve the scientificity and accuracy of hot spot area predictions.

[0047] Furthermore, by accurately grading the number of burning points in the grid to be tested, the grid risk level is accurately distinguished, which more objectively reflects the possibility of regional fires and provides a more accurate data basis for subsequent hot spot area predictions. Compared with the traditional simple classification method, the grid division strategy of the present invention has stronger hierarchical and differentiated recognition capabilities, which can significantly improve the accuracy and reliability of fire risk assessment and provide more intelligent and efficient technical support for remote sensing satellite observation and emergency warning.

[0048] Furthermore, by accurately identifying the types of adjacent grids on the four sides of the second grid, a comprehensive regional correlation analysis was conducted, historical burning points in the bordering parts were detected and the vegetation bordering rate was calculated, thus realizing the dynamic correlation between the geographical environment and fire risk between regions. By comparing the vegetation bordering rate with the preset standard, the grid classification was adjusted intelligently and finely.

[0049] Furthermore, by calculating in detail the vegetation bordering rate between each target adjacent grid and the second grid, the ecological connection and potential fire propagation risk between different grids can be effectively evaluated. By calculating the ratio of the vegetation bordering rate to the grid vegetation area of ​​the second grid, the obtained vegetation bordering rate not only reflects the relative density and distribution of vegetation between regions, but also provides an important basis for judging whether the second grid should cut off part of the area and adjust it to the first grid. It improves the ability to identify fire risk areas and provides a scientific basis for accurate remote sensing satellite resource allocation.

[0050] Furthermore, the accuracy of grid classification is significantly improved through the evaluation of the vegetation bordering rate. When the vegetation bordering rate is greater than or equal to the preset standard bordering rate, the potential fire propagation risk between the second grid and the adjacent first grid can be effectively identified, so that part of the second grid can be corrected and adjusted to the first grid. It can respond more flexibly to different geographical and ecological environmental changes, improve the adaptability and reliability of fire risk prediction, and further enhance the accuracy of hot spot area prediction.

[0051] Furthermore, by clearly distinguishing between dry burning areas and non-dry burning areas, the accuracy and effectiveness of fire prediction are significantly enhanced. By comparing the burning ratio with the preset burning ratio threshold, it is possible to effectively distinguish the burning conditions of vegetation within the grid, predict hot spots, deploy more remote sensing satellites to observe hot spots, and improve the efficiency of remote sensing satellite use.

[0052] Furthermore, by accurately judging whether the current weather is dry and dynamically adjusting the observation focus of remote sensing satellites to ensure efficient use of resources, this adaptive prediction strategy based on weather conditions not only improves the ability to identify potential fire risk areas, but also effectively reduces unnecessary observation costs and optimizes the resource allocation of remote sensing satellites.

[0053] Furthermore, by obtaining the longitude and latitude and burning time of historical burning points recorded by remote sensing satellites in historical observations, accurate positioning and time tracking of fire occurrences in the target area are achieved, ensuring the high quality and accuracy of historical data, and providing a solid data foundation for subsequent grid division and analysis. By accurately calibrating the geographical location of each burning point, the spatial distribution characteristics of fire occurrence can be effectively revealed. Obtaining burning time information can deeply analyze the temporal laws of fire occurrence, providing a scientific basis for the prediction and management of future fire risks.

[0054] Furthermore, through precise grid division technology, high-precision and uniform spatial segmentation of the target area is achieved, laying a solid foundation for the subsequent accurate prediction of hot spot areas. By accurately marking historical burning points to the corresponding grids, not only the precise positioning of the spatial position is achieved, but also a scientific basis is provided for the quantitative analysis of the distribution of burning points, which can significantly improve the accuracy and reliability of hot spot area predictions. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A flowchart of a hotspot area prediction method based on historical observation task data provided by an embodiment of the present invention;

[0056] Figure 2 A flow chart for determining a grid type according to an embodiment of the present invention;

[0057] Figure 3 A flow chart for determining a dry combustion grid and a non-dry combustion grid according to an embodiment of the present invention;

[0058] Figure 4 The present invention is a flowchart for determining the number of combustion points in a grid to be tested according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0060] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0061] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0062] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0063] See also Figure 1 ,like Figure 1 As shown, it is a flow chart of a hot spot area prediction method based on historical observation task data provided by an embodiment of the present invention;

[0064] Specifically, an embodiment of the present invention provides a hotspot area prediction method based on historical observation task data, including:

[0065] Step S1, obtaining the burning position and burning time of the historical burning points observed by the remote sensing satellite in the target area;

[0066] Step S2, dividing the target area into grids according to the geographical location to form a plurality of grids to be tested, and determining the number of combustion points in each grid to be tested according to the combustion position;

[0067] Step S3, determining the grid type of the grid to be tested according to the number of the combustion points, including a first grid, a second grid and a third grid;

[0068] Step S4, determining whether there is a target adjacent grid whose grid type is the first grid among the grids adjacent to the second grid, and if there is a target adjacent grid, determining whether there is the historical burning point in the bordering part, and, if it is determined that there is a historical burning point, calculating the total vegetation bordering area of ​​the bordering part of the second grid and each target adjacent grid, calculating the vegetation bordering rate based on the total vegetation bordering area and the vegetation area of ​​the second grid, and determining whether to divide the second grid into a first grid based on the vegetation bordering rate;

[0069] Step S5, calculating the combustion ratio of the target combustion point in the first grid during the dry period of the year, and comparing the combustion ratio with a preset combustion ratio threshold to determine the combustion status;

[0070] Step S6, determining whether the current weather is dry based on the current real-time temperature and real-time humidity and the corresponding preset temperature and preset humidity, predicting hot spots with a high probability of fire based on the determination result and the combustion conditions, and increasing the use of remote sensing satellites for observing the hot spots.

[0071] Specifically, the preset temperature and preset humidity are standard thresholds for determining whether the current weather is dry. Usually, the preset temperature is 34°C-38°C, and the preset humidity is 30%-50%. In this embodiment, the preset temperature is 34°C, and the preset humidity is 30%, that is, the weather is dry when the temperature is greater than 34°C and the relative humidity of the air is less than 30%. The historical burning point is the location where a fire has occurred in historical observations within the target area. The burning position is the coordinates of the specific location of the historical burning point. The burning time is the specific time when the fire occurred as observed by the remote sensing satellite. The geographical location is the latitude and longitude coordinate range of the target area. The vegetation bordering rate is the area of ​​vegetation bordered by the grid and the adjacent grids as a percentage of the total vegetation area in the grid. ratio, obtain the burning position and burning time of each historical burning point in the target area through remote sensing satellite, determine the number of burning points in each grid to be tested by gridding the target area, determine the grid type of the grid to be tested according to the number of burning points to represent the trend of burning in each grid, determine the vegetation bordering rate of the bordering part according to the grid type of the grid adjacent to the second grid, when there are historical burning points in the bordering part, determine whether to split the area of ​​the second grid into the first grid according to the vegetation bordering rate, determine the weather when the historical burning points in the first grid burn, dry burning or non-dry burning, so as to predict the area observed by the remote sensing satellite according to the current weather.

[0072] Specifically, by performing refined grid division and multi-dimensional analysis on the target area to predict the hotspot areas for observation, the accuracy and pertinence of remote sensing satellite hotspot area predictions are significantly improved. Through historical burning point data, the target area is divided into different types of grids, and the grids are dynamically adjusted according to the distribution characteristics of the burning points in the grids. The vegetation border rate is evaluated according to the regional geographical environment characteristics, which can more accurately identify potential high-risk areas and improve prediction accuracy. By analyzing the time distribution of burning points in the first grid and combining it with current weather conditions, the burning situation can be intelligently distinguished, greatly improving the accuracy of hotspot area predictions. This method can not only dynamically adjust the observation strategy of remote sensing satellites, but also optimize satellite resource allocation, significantly improving observation efficiency and early warning capabilities.

[0073] Please continue reading Figure 2 ,like Figure 2 As shown, it is a flow chart of determining the grid type according to an embodiment of the present invention;

[0074] Specifically, step S3 includes:

[0075] Step S31, comparing the number of combustion points of each of the grids to be tested with a preset minimum number of combustion points and a preset maximum number of combustion points to obtain a comparison result;

[0076] Step S32: determining the grid type of the grid to be tested based on the comparison result.

[0077] Specifically, the grids to be tested are divided into different grid types by preset minimum and maximum numbers of burning points to represent the possible degree of fire that may occur in each grid to be tested.

[0078] Specifically, by strictly comparing the number of burning points in each grid with the preset minimum and maximum number of burning points, a systematic and quantitative classification of grid types is achieved, which can objectively reflect the degree of fire risk in different grid areas, provide a more accurate data basis for subsequent hot spot area predictions, and significantly improve the scientificity and accuracy of hot spot area predictions.

[0079] Specifically, in the step S32, the process of determining the grid type of the grid to be tested based on the comparison result includes:

[0080] If the number of combustion points is greater than the maximum number of combustion points, the grid to be tested is determined as the first grid;

[0081] If the number of combustion points is less than the minimum number of combustion points, the grid to be tested is determined as the third grid;

[0082] If the number of combustion points is neither greater than the maximum number of combustion points nor less than the minimum number of combustion points, the grid to be tested is determined as the second grid.

[0083] Specifically, when the number of burning points in the grid to be tested is less than the minimum burning point, it means that the fire that occurred in the grid area to be tested may be caused by human or natural factors under unexpected circumstances, and the risk of fire occurring again is small. When the number of burning points is between the minimum number of burning points and the maximum number of burning points, it means that the fire in this area may also be a low-probability event, but it may also be due to the initial inaccurate grid division of this area, resulting in the area with high risk of fire being divided together with the area with low risk. When the number of burning points is greater than the maximum burning point, it means that fires often occur in this grid to be tested, and the risk of fire is high.

[0084] In the specific implementation process, the preset minimum number of combustion points is 3, the preset maximum number of combustion points is 8, and the number of combustion points obtained in a certain grid to be tested is 10. If the number of combustion points of the grid to be tested is greater than the maximum number of combustion points, the grid to be tested is determined as the first grid.

[0085] Specifically, by accurately grading the number of burning points in the grid to be tested, the grid risk level is accurately distinguished, which more objectively reflects the possibility of regional fires and provides a more accurate data basis for subsequent hot spot area predictions. Compared with the traditional simple classification method, the grid division strategy of the present invention has stronger hierarchical and differentiated recognition capabilities, which can significantly improve the accuracy and reliability of fire risk assessment and provide more intelligent and efficient technical support for remote sensing satellite observation and emergency warning.

[0086] Please continue reading Figure 3 ,like Figure 3 As shown, it is a flow chart of determining a dry combustion grid and a non-dry combustion grid according to an embodiment of the present invention;

[0087] Specifically, in step S4, it includes:

[0088] Step S41, determining the grid type of the adjacent grids adjacent to the four sides of the second grid;

[0089] Step S42, when there is a first grid in the adjacent grids, determining whether there is a historical burning point in the bordering part;

[0090] Step S43, when there is a historical burning point in the bordering part, obtaining the total area of ​​vegetation bordering the bordering part between the target adjacent grid and the second grid, and calculating the vegetation bordering rate;

[0091] Step S44, comparing the vegetation bordering rate with a preset standard bordering rate to obtain a comparison result, and determining whether to correct a part of the second grid to the first grid based on the comparison result.

[0092] Specifically, the grid type of the adjacent grid that shares the same side with the four adjacent sides of the second grid is determined. When the first grid exists in the adjacent grid, it is detected whether there are any historical burning points in the vegetation part bordering the second grid and the adjacent first grid. When there is a historical burning and the calculated vegetation bordering rate is greater than the preset standard bordering rate, it means that the grid division within this range is unreasonable, and the second grid is partially corrected to the first grid.

[0093] Specifically, by accurately identifying the adjacent grid types on the four sides of the second grid, a comprehensive regional correlation analysis was conducted, historical burning points in the bordering parts were detected and the vegetation bordering rate was calculated, thus realizing the dynamic correlation between the geographical environment and fire risk between regions. By comparing the vegetation bordering rate with the preset standard, the grid classification was adjusted intelligently and finely.

[0094] Specifically, in step S43, the process of calculating the vegetation bordering rate includes:

[0095] Calculating the vegetation bordering area of ​​each of the target adjacent grids and the second grid;

[0096] Calculating the sum of the bordering areas of each vegetation to obtain the total bordering area of ​​the vegetation;

[0097] The ratio of the total vegetation bordering area to the grid vegetation area of ​​the second grid is calculated to obtain the vegetation bordering rate.

[0098] In the specific implementation process, there are two target adjacent grids adjacent to a second grid. The vegetation bordering areas of the second grid and the two target adjacent grids are determined to be 60,000 square meters and 100,000 square meters respectively. The total vegetation bordering area of ​​60,000 square meters plus 100,000 square meters is calculated to be 160,000 square meters. The grid vegetation area within the second grid is 500,000 square meters. The vegetation bordering rate of the second grid is the ratio of the total vegetation bordering area of ​​160,000 square meters to the grid vegetation area of ​​500,000 square meters, which is 32%.

[0099] Specifically, by calculating in detail the vegetation bordering rate between each target adjacent grid and the second grid, the ecological connection and potential fire propagation risk between different grids can be effectively evaluated. By calculating the ratio of the vegetation bordering rate to the grid vegetation area of ​​the second grid, the obtained vegetation bordering rate not only reflects the relative density and distribution of vegetation between regions, but also provides an important basis for judging whether the second grid should cut part of the area and adjust it to the first grid. It improves the ability to identify fire risk areas and provides a scientific basis for accurate remote sensing satellite resource allocation.

[0100] Specifically, in step S44, the process of determining whether to correct a part of the second grid to the first grid based on the comparison result includes:

[0101] If the vegetation bordering rate is greater than or equal to the standard bordering rate, it is determined to correct a part of the second grid into the first grid.

[0102] Specifically, if the vegetation bordering rate is less than the standard bordering rate, it is determined not to correct the partial area of ​​the second grid to the first grid.

[0103] In the specific implementation process, the preset standard bordering rate is 25%, and the vegetation bordering rate of a second grid is 32%, which is greater than the standard bordering rate. Therefore, it is determined that part of the second grid will be corrected to the first grid.

[0104] Specifically, the accuracy of grid classification is significantly improved by evaluating the vegetation bordering rate. When the vegetation bordering rate is greater than or equal to the preset standard bordering rate, the potential fire propagation risk between the second grid and the adjacent first grid can be effectively identified, so that part of the second grid can be corrected and adjusted to the first grid. It can respond more flexibly to different geographical and ecological environmental changes, improve the adaptability and reliability of fire risk prediction, and further enhance the accuracy of hot spot area prediction.

[0105] Specifically, in step S5, the process of determining the combustion condition includes:

[0106] Determining whether the burning time of the historical burning points in the first grid is within the dry time period of the year;

[0107] Calculating a ratio of a target quantity in each of the first grids within a drying time period to the first quantity to obtain the combustion ratio;

[0108] The combustion ratio is compared with the combustion ratio threshold to obtain a comparison result, and the combustion condition is determined based on the comparison result, wherein:

[0109] If the combustion ratio is less than or equal to the combustion ratio threshold, determining that the combustion condition is non-dry combustion;

[0110] If the combustion ratio is greater than the combustion ratio threshold, it is determined that the combustion condition is dry combustion.

[0111] Specifically, the dry time period is the time period when the temperature reaches a certain temperature and the humidity reaches a certain humidity. In the specific implementation process, it can be a time period when the temperature is greater than 34°C and the relative humidity of the air is less than 30%. It is determined that there are 20 historical combustion points in a first grid, and the number of grids where combustion occurs in the dry time period is 18. The calculated combustion ratio is 18 divided by 20, which is 90%. The preset combustion ratio threshold is 60%. The combustion ratio of the first grid is greater than the combustion ratio threshold, and the combustion condition is determined to be dry combustion.

[0112] Specifically, by clearly distinguishing between dry burning areas and non-dry burning areas, the accuracy and effectiveness of fire prediction are significantly enhanced. By comparing the burning ratio with the preset burning ratio threshold, it is possible to effectively distinguish the burning of vegetation within the grid, predict hot spots, deploy more remote sensing satellites to observe hot spots, and improve the efficiency of remote sensing satellite use.

[0113] Specifically, in step S6, the process of predicting the hotspot area with a high probability of fire occurrence based on the determination result and the combustion situation includes:

[0114] If the current weather is dry, the hot spot area observed by the remote sensing satellite is predicted to be a dry burning area composed of the first grids where the burning conditions are dry burning;

[0115] If the current weather is not dry, the hot spot area observed by the remote sensing satellite is predicted to be a non-dry combustion area composed of the first grids where the combustion conditions are dry combustion.

[0116] Specifically, different predictions are made for the hotspot areas of fire that are being observed by remote sensing satellites depending on whether the current weather is dry or not. When the weather is dry, it is predicted that the dry burning area composed of the first grid where all burning conditions are dry burning is the hotspot area. When the weather is not dry, it is predicted that the non-dry burning area composed of the first grid where all burning conditions are dry burning is the hotspot area.

[0117] Specifically, by accurately judging whether the current weather is dry and dynamically adjusting the observation focus of remote sensing satellites, efficient use of resources can be ensured. This adaptive prediction strategy based on weather conditions not only improves the ability to identify potential fire risk areas, but also effectively reduces unnecessary observation costs and optimizes the resource allocation of remote sensing satellites.

[0118] Specifically, in step S1, the longitude and latitude coordinates of the historical burning point in the historical observation of the remote sensing satellite are obtained as the burning position, and the time when the burning occurred at the historical burning point observed by the remote sensing satellite is obtained as the burning time.

[0119] Specifically, by obtaining the longitude and latitude and burning time of historical burning points recorded by remote sensing satellites in historical observations, we can accurately locate and track the occurrence of fires in the target area, ensure the high quality and accuracy of historical data, and provide a solid data foundation for subsequent grid division and analysis. By accurately calibrating the geographical location of each burning point, we can effectively reveal the spatial distribution characteristics of fire occurrence. Obtaining burning time information can deeply analyze the temporal laws of fire occurrence, providing a scientific basis for the prediction and management of future fire risks.

[0120] Please continue reading Figure 4 ,like Figure 4 As shown, it is a flow chart of determining the number of combustion points in a grid to be tested according to an embodiment of the present invention;

[0121] Specifically, the step S2 includes:

[0122] Step S21, dividing the target area into a plurality of grids to be measured of equal size at equal intervals according to the geographical location according to the preset grid division accuracy;

[0123] Step S22, marking each of the historical combustion points in the grid to be tested according to the combustion position;

[0124] Step S23, obtaining the number of the historical combustion points in each of the grids to be tested to obtain the number of combustion points.

[0125] Specifically, the preset grid division accuracy is divided according to certain longitude and latitude values. In the specific implementation process, it can be a grid formed by longitude and latitude of 0.005°-0.05°. In this embodiment, the longitude and latitude of 0.02° are selected to divide the grid. In the specific implementation process, the target area is an area of ​​76°-77° east longitude and 36°-37° north latitude. The target area is divided into a 0.02°×0.02° grid, which is divided into 50 parts in terms of longitude and latitude, and the target area is divided into a total of 2500 grids.

[0126] Specifically, through precise grid division technology, high-precision and uniform spatial segmentation of the target area is achieved, laying a solid foundation for the subsequent accurate prediction of hot spot areas. By accurately marking historical burning points to corresponding grids, not only the precise positioning of spatial positions is achieved, but also a scientific basis is provided for the quantitative analysis of the distribution of burning points, which can significantly improve the accuracy and reliability of hot spot area predictions.

[0127] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0128] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A hotspot area prediction method based on historical observation task data, characterized in that: include: Step S1, obtaining the burning position and burning time of the historical burning points observed by the remote sensing satellite in the target area; Step S2, dividing the target area into grids according to the geographical location to form a plurality of grids to be tested, and determining the number of combustion points in each grid to be tested according to the combustion position; Step S3, determining the grid type of the grid to be tested according to the number of the combustion points, including a first grid, a second grid and a third grid; Step S4, determining whether there is a target adjacent grid whose grid type is the first grid among the grids adjacent to the second grid, and if there is a target adjacent grid, determining whether there is the historical burning point in the bordering part, and, if it is determined that there is a historical burning point, calculating the total vegetation bordering area of ​​the bordering part of the second grid and each target adjacent grid, calculating the vegetation bordering rate based on the total vegetation bordering area and the vegetation area of ​​the second grid, and determining whether to correct a part of the second grid to the first grid based on the vegetation bordering rate; Step S5, calculating the combustion ratio of the target combustion point in the first grid during the dry period of the year, and comparing the combustion ratio with a preset combustion ratio threshold to determine the combustion status; Step S6, determining whether the current weather is dry based on the current real-time temperature and real-time humidity and the corresponding preset temperature and preset humidity, predicting the hotspot area where the fire may occur based on the determination result and the combustion situation, and increasing the use of remote sensing satellites for observing the hotspot area.

2. The hotspot area prediction method based on historical observation task data according to claim 1 is characterized in that: In the step S3, it includes: Step S31, comparing the number of combustion points of each of the grids to be tested with a preset minimum number of combustion points and a preset maximum number of combustion points to obtain a comparison result; Step S32: determining the grid type of the grid to be tested based on the comparison result.

3. The hotspot area prediction method based on historical observation task data according to claim 2 is characterized in that: In the step S32, the process of determining the grid type of the grid to be tested based on the comparison result includes: If the number of burning points is greater than the maximum number of burning points, it is determined as the first grid; If the number of burning points is less than the minimum number of burning points, it is determined to be the third grid; If the number of combustion points is neither greater than the maximum number of combustion points nor less than the minimum number of combustion points, it is determined as the second grid.

4. The hotspot area prediction method based on historical observation task data according to claim 1 is characterized in that: In the step S4, it includes: Step S41, determining the grid type of the adjacent grids adjacent to the four sides of the second grid; Step S42, when there is a first grid in the adjacent grids, determining whether there is a historical burning point in the bordering part; Step S43, when there is a historical burning point in the bordering part, obtaining the total area of ​​vegetation bordering the bordering part between the target adjacent grid and the second grid, and calculating the vegetation bordering rate; Step S44, comparing the vegetation bordering rate with a preset standard bordering rate to obtain a comparison result, and determining whether to correct a portion of the second grid to the first grid based on the comparison result.

5. The hotspot area prediction method based on historical observation task data according to claim 4 is characterized in that: In step S43, the process of calculating the vegetation bordering rate includes: Calculating the vegetation bordering area of ​​each of the target adjacent grids and the second grid; Calculating the sum of the bordering areas of each vegetation to obtain the total bordering area of ​​the vegetation; The ratio of the total vegetation bordering area to the grid vegetation area of ​​the second grid is calculated to obtain the vegetation bordering rate.

6. The hotspot area prediction method based on historical observation task data according to claim 4 is characterized in that: In step S44, the process of determining whether to correct a part of the second grid to the first grid based on the comparison result includes: If the vegetation bordering rate is greater than or equal to the standard bordering rate, it is determined to correct a part of the second grid into the first grid.

7. The hotspot area prediction method based on historical observation task data according to claim 1 is characterized in that: In step S5, the process of determining the combustion condition includes: Determining whether the burning time of the historical burning points in the first grid is within the dry time period of the year; Calculating the ratio of the target quantity in the drying time period to the first quantity in each of the first grids to obtain the combustion ratio; The combustion ratio is compared with the combustion ratio threshold to obtain a comparison result, and the combustion condition is determined based on the comparison result, wherein: If the combustion ratio is less than or equal to the combustion ratio threshold, determining that the combustion condition is non-dry combustion; If the combustion ratio is greater than the combustion ratio threshold, it is determined that the combustion condition is dry combustion.

8. The hotspot area prediction method based on historical observation task data according to claim 1 is characterized in that: In step S6, the process of predicting the hotspot area with a high probability of fire occurrence based on the determination result and the combustion situation includes: If the current weather is dry, the hot spot area observed by the remote sensing satellite is predicted to be a dry burning area composed of the first grids where the burning conditions are dry burning; If the current weather is not dry, the hot spot area observed by the remote sensing satellite is predicted to be a non-dry combustion area composed of the first grids where the combustion conditions are dry combustion.

9. The hotspot area prediction method based on historical observation task data according to claim 1 is characterized in that: In the step S1, the longitude and latitude coordinates of the historical burning point in the historical observation of the remote sensing satellite are obtained as the burning position, and the time when the burning occurred at the historical burning point observed by the remote sensing satellite is obtained as the burning time.

10. The hotspot area prediction method based on historical observation task data according to claim 1, characterized in that: In the step S2, it includes: Step S21, dividing the target area into a plurality of grids to be measured of equal size at equal intervals according to the geographical location according to the preset grid division accuracy; Step S22, marking each of the historical combustion points in the grid to be tested according to the combustion position; Step S23, obtaining the number of the historical combustion points in each of the grids to be tested to obtain the number of combustion points.

Images