WUI division method, device and equipment based on house wild fire risk and storage medium

Abstract

The application provides a WUI division method and device based on house wild fire risk, equipment and storage medium, determines the weighted fuel grade of each fuel grid in the region to be divided; for each house in the region to be divided, the building wild fire risk index of the house is calculated and obtained; for each fuel grid, the vegetation danger index of the fuel grid is calculated and obtained; from all the houses in the region to be divided, the houses with building wild fire risk index greater than a preset first threshold value are screened out as risk houses; for each risk house, from all the fuel grids falling within the buffer area corresponding to the risk house, the fuel grids with vegetation danger index greater than a preset second threshold value are screened out as risk fuel grids corresponding to the risk house; for each risk house, the risk house and the risk fuel grid corresponding to the risk house are regionally merged to obtain a plurality of forest town junction domains in the region to be divided. The scheme of the application improves the accuracy of forest town junction domain division.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wild fire protection, and particularly relates to a WUI division method and device based on house wild fire risk, equipment and storage medium. BACKGROUND

[0002] In recent years, wild fires have a major negative impact on global ecological environment safety, wildlife protection, human health maintenance and economic and social development. Whether caused by human factors or natural factors, when the fire in nature is out of control and spreads from the forest to the building area, it is easy to evolve into a heavy forest fire or a large-scale building fire, becoming a coupling emergency event across natural disasters and accident disasters. This risk is concentrated in the area where houses and natural vegetation such as forests meet or mix, which is called the wildland-urban interface (WUI).

[0003] As the zone of conflict and risk concentration between humans and the environment, when a wild fire occurs, the WUI often becomes the main place where personnel casualties, house damage and fire extinguishing expenses occur. The WUI area exists universally in the global range, and with the change of human land use patterns (such as urban expansion, industrial facility construction and increase of residential areas), the area of the WUI continues to grow, so that more human life, property and infrastructure are facing more obvious wild fire risks. Therefore, accurately dividing the WUI area map has important scientific significance and practical value for wild fire prevention and control and fire risk management.

[0004] In the prior art, the research contents of the forest-urban interface mainly include WUI definition, mapping method, management strategy, fire risk assessment and intervention priority assessment. The common point of the existing method is to combine two types of land cover (buildings and vegetation), and then use geographic information system for spatial analysis. Although the definition of WUI is relatively consistent in many studies, the methods and parameter settings for WUI division are quite different. For example, how to determine the specific location of buildings and vegetation, how to determine the danger threshold, how to select a reasonable buffer distance or moving window size, etc.

[0005] In the prior art, the WUI division method is mostly based on the method of building density priority, and is refined and optimized on this basis. However, the existing method is limited by the subjective definition of building density and vegetation coverage, and the accuracy of WUI division is poor. SUMMARY

[0006] The present application provides a WUI division method, device, equipment and storage medium based on house wild fire risk, to solve the defect that the accuracy of WUI division in the prior art is poor, to realize more fine and practical WUI division, and to improve the accuracy of WUI division.

[0007] The application provides a WUI division method based on house wild fire risk, comprising the following steps:

[0008] Divide the to-be-divided region according to a predetermined resolution to obtain a plurality of fuel grids, and determine the weighted fuel grade of each fuel grid;

[0009] For each house in the to-be-divided region, a buffer zone corresponding to the house is established, and the building wild fire risk index of the house is calculated based on the weighted fuel grade of each fuel grid falling in the buffer zone corresponding to the house;

[0010] For each fuel grid, a buffer zone corresponding to the fuel grid is established, and the vegetation danger index of the fuel grid is calculated based on the building risk value of each house falling in the buffer zone corresponding to the fuel grid;

[0011] From all the houses in the to-be-divided region, the houses with building wild fire risk indexes greater than a preset first threshold value are screened out as risk houses;

[0012] For each risk house, from all the fuel grids falling in the buffer zone corresponding to the risk house, the fuel grids with vegetation danger indexes greater than a preset second threshold value are screened out as risk fuel grids corresponding to the risk house;

[0013] For each risk house, the risk house and the risk fuel grids corresponding to the risk house are regionally merged to obtain a plurality of forest town junction domains in the to-be-divided region.

[0014] According to the WUI division method based on house wild fire risk provided by the application, the determination of the weighted fuel grade of each fuel grid comprises:

[0015] According to the suppression difficulty of different land cover types, the cost weight value corresponding to different land cover types is determined;

[0016] The aggregation index corresponding to each fuel grid is calculated;

[0017] For each fuel grid, the weighted fuel grade of the fuel grid is determined according to the cost weight value corresponding to the land cover type of the fuel grid and the aggregation index corresponding to the fuel grid.

[0018] According to the WUI division method based on house wild fire risk provided by the application, the calculation of the building wild fire risk index of the house based on the weighted fuel grade of each fuel grid falling in the buffer zone corresponding to the house comprises:

[0019] According to the weighted fuel grade of each fuel grid falling in the buffer area corresponding to the house and the buffer distance of each fuel grid, the influence fuel grid corresponding to the house is obtained from all fuel grids falling in the buffer area corresponding to the house, wherein the buffer distance of the fuel grid is the distance between the fuel grid and the house.

[0020] According to the weighted fuel grade of each influence fuel grid corresponding to the house, the buffer distance, and the number of land cover types of the influence fuel grid corresponding to the house, the building wild fire risk index of the house is calculated.

[0021] According to the building risk value of each house falling in the buffer area corresponding to the fuel grid, the vegetation danger index of the fuel grid is calculated, and the method comprises the following steps:

[0022] All houses falling in the buffer area corresponding to the fuel grid are counted.

[0023] According to the building risk value of each house falling in the buffer area corresponding to the fuel grid and the building area of each house, the vegetation danger index of the fuel grid is calculated.

[0024] According to the building risk value of each house falling in the buffer area corresponding to the fuel grid and the building area of each house, the vegetation danger index of the fuel grid is calculated.

[0025] According to the building risk value of each house falling in the buffer area corresponding to the fuel grid and the building area of each house, the vegetation danger index of the fuel grid is calculated.

[0026] The effectiveness of the plurality of forest-town interface domains in the to-be-divided region is verified by applying a single single-factor method.

[0027] According to the building risk value of each house falling in the buffer area corresponding to the fuel grid and the building area of each house, the vegetation danger index of the fuel grid is calculated.

[0028] The plurality of forest-town interface domains in the to-be-divided region are filled to divide the non-forest-town interface domains completely surrounded by the forest-town interface domains into forest-town interface domains.

[0029] The application further provides a WUI division device based on house wild fire risk, comprising the following modules:

[0030] a grid division module, configured to divide the to-be-divided region according to a predetermined resolution, to obtain a plurality of fuel grids, and to determine a weighted fuel grade of each fuel grid;

[0031] a first calculation module, configured to, for each house in the to-be-divided region, establish a buffer zone corresponding to the house, and to calculate a building wild fire risk index of the house based on the weighted fuel grade of each fuel grid falling within the buffer zone corresponding to the house;

[0032] a second calculation module, configured to, for each fuel grid, establish a buffer zone corresponding to the fuel grid, and to calculate a vegetation danger index of the fuel grid based on the building risk value of each house falling within the buffer zone corresponding to the fuel grid;

[0033] a first screening module, configured to, from all the houses in the to-be-divided region, screen out a house with a building wild fire risk index greater than a preset first threshold value, as a risk house;

[0034] a second screening module, configured to, for each risk house, from all the fuel grids falling within the buffer zone corresponding to the risk house, screen out a fuel grid with a vegetation danger index greater than a preset second threshold value, as a risk fuel grid corresponding to the risk house;

[0035] a region merging module, configured to, for each risk house, perform region merging on the risk house and the risk fuel grid corresponding to the risk house, to obtain a plurality of forest town junctions in the to-be-divided region.

[0036] The present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the WUI division method based on house wild fire risk according to any one of the above when executing the computer program.

[0037] The present application also provides a non-transitory computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the WUI division method based on house wild fire risk according to any one of the above.

[0038] The present application also provides a computer program product, comprising a computer program, wherein the computer program is executed by a processor to implement the WUI division method based on house wild fire risk according to any one of the above.

[0039] The application provides a WUI division method based on house wild fire risk, a WUI division device based on house wild fire risk, a WUI division equipment based on house wild fire risk and a storage medium. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0041] Figure 1 FIG. 1 is a flowchart of the WUI division method based on house wild fire risk provided by the present application.

[0042] Figure 2 FIG. 2 is a structural diagram of the WUI division device based on house wild fire risk provided by the present application.

[0043] Figure 3 FIG. 3 is a structural diagram of the electronic equipment provided by the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the present application more clear, the technical solutions in the present application will be described clearly and completely in the following with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0045] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific examples. The following specific examples can be combined with each other, and the same or similar concepts or processes can not be described again in some examples. The following will be described in combination with Figure 1 The present application describes a WUI division method based on house wild fire risk.

[0046] In practical applications, the execution subject of the WUI division method based on house wild fire risk can be a WUI division device based on house wild fire risk. The implementation mode of the WUI division device based on house wild fire risk has many kinds, such as being realized by a computer program, for example, application software, etc.; or, for example, a chip, etc. It can also be realized as a medium storing a related computer program, for example, a U disk, a cloud disk, etc.; or, it can also be realized by an entity device integrated or installed with a related computer program, such as a server, a smart device, etc.

[0047] Figure 1 is a flowchart of the WUI division method based on house wild fire risk provided by the present application, as Figure 1 shown, the method comprises steps 101 to 109.

[0048] Step 101, divide the region to be divided according to a predetermined resolution to obtain a plurality of fuel grids.

[0049] Among them, the resolution refers to the spatial resolution of the land cover data when performing geographic information system (GIS) analysis. Spatial resolution refers to the size of the smallest unit in an image or data set, which determines the size of the smallest feature that can be identified. In geographic information systems, resolution is often used to describe the accuracy of raster data, that is, the actual ground area represented by each grid cell (pixel). In practice, resolution refers to the degree of spatial detail of data, that is, the geographical range covered by each data point.

[0050] For example, the region to be divided can be divided into a plurality of grids according to a resolution of 30 meters, that is, each grid cell represents a ground area of 30 meters x 30 meters. Such resolution allows researchers to evaluate and quantify the wild fire risk of each independent house and its surrounding vegetation in units of 30 meters.

[0051] In practical applications, dividing the region to be divided according to a predetermined resolution can obtain a plurality of grids with equal areas, and the plurality of grids include fuel grids and non-fuel grids. Further, for each fuel grid, a weighted fuel grade is determined. For non-fuel grids, the weighted fuel grade is assigned a preset value in this embodiment, for example, the weighted fuel grade is assigned a preset value of 10.

[0052] Step 102, determining a weighted fuel rank of each fuel grid.

[0053] For example, all combustible land cover types are extracted from the GlobeLand30-2020 dataset, including but not limited to shrubs, grasslands, vegetation wetlands, tundra, herbaceous plants, and all types of forests. Non-fuel land cover types include but are not limited to farmland, true wetlands, pasture, sparse vegetation on rock, bare soil, impervious surface, bare land, rock, snow or ice, barren, water, and unknown land cover types.

[0054] Specifically, for each fuel grid, the weighted fuel rank of the fuel grid is determined by considering the land cover type of the vegetation in the fuel grid and the horizontal fuel connectivity of the fuel grid. It can be understood that the weighted fuel rank of each fuel grid takes into account the land cover type and connectivity corresponding to the fuel grid, providing important data support for subsequent wild fire risk assessment.

[0055] As an example, in one possible implementation, the above step 102 includes:

[0056] According to the suppression difficulty of different land cover types, determine the cost weight value corresponding to different land cover types;

[0057] Calculate the aggregation index corresponding to each fuel grid;

[0058] For each fuel grid, according to the cost weight value corresponding to the land cover type of the fuel grid and the aggregation index corresponding to the fuel grid, determine the weighted fuel rank of the fuel grid.

[0059] The suppression difficulty of land cover types refers to the difficulty of fire suppression or control for a specific land cover type in wild fire management. Specifically, different types of vegetation have different combustion characteristics, some vegetation is easier to ignite, burns faster, or is more difficult to extinguish, so the suppression difficulty of different land cover types is different.

[0060] In practical applications, considering the differences in the degree of combustion and the speed of spread of different vegetation around houses when a wild fire occurs, different land cover types are ranked according to the suppression difficulty of different land cover types. Specifically, this embodiment uses a variable width buffer technique to determine the cost weight value corresponding to different land cover types. The variable width buffer technique uses cost distance calculation to link different cost weights with land cover types in GlobeLand30-2020. The cost weights corresponding to different land cover types are shown in Table 1.

[0061] Table 1

[0062]

[0063] where fc is the Fractional Cover, which is an index representing the degree of vegetation cover, used to describe the proportion of ground covered by vegetation in a particular area. The value of fc ranges from 0 to 1, where 0 means no vegetation cover and 1 means complete cover.

[0064] Further, the horizontal fuel connectivity of each fuel grid is evaluated, i.e. the aggregation index corresponding to each fuel grid is calculated.

[0065] where the aggregation index (AI) provides a measure of the connectivity or aggregation of fuel dispersed within an area, which also provides a reference for the ease of fire spread throughout the landscape. For example, the aggregation index of all fuel grids in A city is calculated in a moving window of size 5*5, and the calculation formula of the aggregation index is as follows:

[0066]

[0067] where, the aggregation degree of the corresponding fuel class , i.e. the sum of the adjacent pairs of pixels of all fuel classes in the 5*5 window. By dividing by , the proportion of the number of similar adjacent patches of the current landscape type relative to the maximum value is represented. Then, this proportion is multiplied by 100 to obtain the percentage form of the aggregation index (AI), and the value of the aggregation index ranges from 0 (no aggregation, i.e. each unit is isolated) to 100 (complete aggregation, i.e. fuel is continuous).

[0068] Further, the aggregation index is classified simply, specifically, AI>90 is classified as "high aggregation" and assigned a value of 0; 0<AI ≤ 90 is classified as "lower aggregation" and assigned a value of 1; AI = 0 is classified as "no aggregation" and assigned a value of 2.

[0069] It can be understood that according to the above Table 1, for each fuel grid, according to the land cover type of the fuel grid, the cost weight value corresponding to the land cover type of the fuel grid can be determined.

[0070] Further, for each fuel grid, a weighted fuel rank of the fuel grid is determined according to the cost weight value corresponding to the land cover type of the fuel grid and the aggregation index corresponding to the fuel grid. Specifically, for each fuel grid, the weighted fuel rank of each fuel grid is calculated by combining the cost weight value corresponding to the land cover type of the fuel grid and the aggregation index corresponding to the fuel grid. For example, the weighted fuel rank value of a fuel grid with a high aggregation index (AI value of 0) and an open coniferous forest land cover type (rank of 1) is 1. The weighted fuel rank value of a non-fuel grid is assigned as 10.

[0071] It can be understood that for each fuel grid, a weighted fuel rank of the fuel grid is determined according to the cost weight value corresponding to the land cover type of the fuel grid and the aggregation index corresponding to the fuel grid. The calculation of the weighted fuel rank integrates the connectivity and suppression difficulty of the fuel, providing a more refined risk indicator for wild fire risk assessment and WUI division. This comprehensive assessment helps to identify areas with high fire risk and provides a scientific basis for developing effective fire prevention and response strategies.

[0072] Step 103, for each house in the area to be divided, a buffer zone corresponding to the house is established.

[0073] In practical applications, for each house in the area to be divided, a buffer zone corresponding to the house is established, which means creating a virtual boundary area around each building in a geographic information system (GIS). This area is usually a circular or polygonal area centered on the building and extending a certain distance outward. This buffer zone is used to assess and quantify the wild fire risk of each individual house and its surrounding vegetation.

[0074] It can be understood that the buffer zone can be circular, square or other polygonal, and the specific shape depends on the research needs and geographical features.

[0075] In an example, the buffer zone corresponding to the house is an annular buffer zone with a preset radius.

[0076] Specifically, the size of the buffer zone can be determined according to the research purpose and actual needs. For example, different levels of buffer zones can be set, such as 2400 meters, 1200 meters, 800 meters, etc.

[0077] Further, based on the building footprint data, the wild fire risk of each house is quantitatively analyzed by calculating the building risk index, which realizes the assessment of the specific wild fire risk of each house in the study area. This not only helps managers to more intuitively and finely understand the distribution of wild fire risk, but also provides a scientific basis for developing targeted building fire prevention strategies and emergency plans.

[0078] Step 104, based on the weighted fuel class of each fuel grid falling within the buffer zone corresponding to the house, calculate the building wild fire risk index of the house.

[0079] As an example, in one possible implementation, the above-mentioned step 104 comprises:

[0080] According to the weighted fuel class of each fuel grid falling within the buffer zone corresponding to the house and the buffer distance of each fuel grid, filter the impact fuel grids corresponding to the house from all fuel grids falling within the buffer zone corresponding to the house; wherein the buffer distance of a fuel grid is the distance between the fuel grid and the house.

[0081] According to the weighted fuel class of each impact fuel grid corresponding to the house, the buffer distance, and the number of land cover types of the impact fuel grids corresponding to the house, calculate the building wild fire risk index of the house.

[0082] It can be understood that the wild vegetation with the greater fuel class can affect a larger range, and the buffer zone class, the buffer distance, and the corresponding effective weighted fuel class are shown in Table 2.

[0083] Table 2

[0084]

[0085] Specifically, according to the buffer distance of each fuel grid, the buffer zone class corresponding to each grid can be determined, and further, it is determined whether the weighted fuel class corresponding to each fuel grid is effective, and if so, the fuel grid with the effective weighted fuel class is taken as the impact fuel grid corresponding to the house.

[0086] In combination with Table 2, for example, fuel grid A is 1200 meters away from house 1, and fuel grid B is 800 meters away from house 1. The buffer distance of fuel grid A is 1200 meters, and the weighted fuel class of fuel grid A is 5. According to Table 2, the buffer distance of 1200 meters corresponds to the buffer zone class of 2, and the buffer zone class of 2 corresponds to the effective weighted fuel class of 1 and 2. It can be seen that the weighted fuel class of fuel grid A is invalid, and fuel grid A is not the impact fuel grid of house 1. For another example, the buffer distance of fuel grid B is 800 meters, and the weighted fuel class of fuel grid B is 2. According to Table 2, the buffer distance of 800 meters corresponds to the buffer zone class of 3, and the buffer zone class of 2 corresponds to the effective weighted fuel class of 1, 2 and 3. It can be seen that the weighted fuel class of fuel grid B is valid, and fuel grid B is the impact fuel grid of house 1.

[0087] Further, based on the influence of fuel classes in different buffer zones around the building, a Building Wildfire Risk Index (BWRI) for each house is calculated. The lower the weighted fuel class of the vegetation, the greater the potential risk, while considering the distance of dangerous vegetation to the house, the farther the distance, the smaller the risk.

[0088] Specifically, the Building Wildfire Risk Index of a house is calculated based on the weighted fuel class of each influence fuel grid corresponding to the house, the buffer distance, and the number of land cover types of the influence fuel grid corresponding to the house. For example, the calculation formula of the Building Wildfire Risk Index is as follows:

[0089]

[0090] where b is the buffer zone level, f is the weighted fuel class, and n is the number of land cover types of the influence fuel grid corresponding to the house.

[0091] In this embodiment, the Building Wildfire Risk Index of a house is calculated based on the weighted fuel class of each influence fuel grid corresponding to the house, the buffer distance, and the number of land cover types of the influence fuel grid corresponding to the house. This risk assessment method provides a specific assessment of the wildfire risk of houses in different areas, which can help local governments and residents to take appropriate preventive measures, such as adding fire fighting facilities, improving vegetation management or re-planning the layout of the area, to reduce the potential fire risk.

[0092] Step 105, for each fuel grid, a buffer zone corresponding to the fuel grid is established.

[0093] Step 106, based on the building risk value of each house falling within the buffer zone corresponding to the fuel grid, a Vegetation Danger Index of the fuel grid is calculated.

[0094] When a wildfire occurs, a crucial factor is whether there is flammable vegetation around the building, which directly determines whether the wildfire can spread and spread. Therefore, it is particularly important to explore and understand the spatial distribution of wild vegetation in the area and the fire risk posed by adjacent buildings. In order to more accurately assess this risk, the present application further calculates the Vegetation Danger Index (VDI) of the fuel grid based on the Building Risk Index. The Vegetation Danger Index is used to measure the degree of wildfire threat posed by wild vegetation to surrounding houses.

[0095] For the convenience of calculation, in this embodiment, firstly, the land cover data (GlobeLand30-2020 dataset) is subjected to a raster-to-point operation, and then a buffer zone corresponding to each grid point is established according to the weighted fuel grid level. Finally, all houses falling within the buffer zone corresponding to the grid point (houses falling within the buffer zone or having an overlapping part with the buffer zone) are counted, and the vegetation danger index of the fuel grid is calculated.

[0096] As an example, in one possible implementation, the above step 106 comprises:

[0097] counting all houses falling within the buffer zone corresponding to the fuel grid;

[0098] calculating the vegetation danger index of the fuel grid according to the building risk value of each house falling within the buffer zone corresponding to the fuel grid and the building area of each house.

[0099] By way of example, the calculation formula of the vegetation danger index is as follows:

[0100]

[0101] wherein BWRI is the building risk value of each house falling within the buffer zone corresponding to the fuel grid, and A represents the area of the house (unit: square meter). Considering that the product of the building risk index and the building area may have a huge difference in different grids, the present application adopts a logarithmic processing method. This processing can effectively reduce the gap between data, making the danger level between different grids more comparable, so as to obtain a more balanced and easy-to-understand index.

[0102] Step 107, from all houses in the region to be divided, houses with a building wild fire risk index greater than a preset first threshold value are screened out as risk houses.

[0103] Step 108, for each risk house, from all fuel grids falling within the buffer zone corresponding to the risk house, fuel grids with a vegetation danger index greater than a preset second threshold value are screened out as risk fuel grids corresponding to the risk house.

[0104] Step 109, for each risk house, the risk house and the risk fuel grid corresponding to the risk house are subjected to region merging, to obtain a plurality of forest-town interface domains in the region to be divided.

[0105] In actual application, in order to reduce the risk of structure loss during a wild fire, in the WUI division process, attention is first paid to houses, and then spread outward from the houses. Specifically, the houses are preliminarily screened through the building risk index, and then attention is paid to the vegetation that has an influence on the houses, so that the region that is more likely to pose a threat to humans in a wild fire can be more scientifically divided.

[0106] It should be noted that the first threshold value and the second threshold value are set in advance according to the WUI area demand, and in practice, they can be adjusted according to the actual WUI area demand. For example, the second threshold value can be 0, and the fuel grid with a vegetation danger index greater than 0 is taken as the risk fuel grid corresponding to the risk house.

[0107] In this embodiment, by dividing the to-be-divided area according to a predetermined resolution, a plurality of fuel grids are obtained, and the weighted fuel grade of each fuel grid is determined, so as to realize the differentiation of the risk grade of each fuel grid, which is beneficial to the more fine management of wild fire; further, based on the weighted fuel grade of each fuel grid, the building wild fire risk index of each house in the to-be-divided area and the vegetation danger index of each fuel grid are calculated, so as to realize the risk quantification evaluation of each house and the vegetation around the house; further, according to the building wild fire risk index and the vegetation danger index, the risk house and the risk fuel grid corresponding to the risk house are screened out, which is helpful to optimize the allocation of emergency resources and ensure that the response can be quickly and effectively when the fire occurs. Further, each risk house and each risk fuel grid corresponding to the risk house are regionally merged to obtain a plurality of forest town junction domains in the to-be-divided area. Therefore, the scheme of the present application realizes fine and practical WUI division, improves the accuracy of WUI division, and provides more scientific and effective decision support for wild fire management.

[0108] In addition, in a possible implementation, after the step 109, the method further includes:

[0109] applying a single factor at a time method to verify the effectiveness of the plurality of forest town junction domains in the to-be-divided area.

[0110] The single factor at a time method (One Factor At a Time, OFAT) is an experimental design and analysis method that studies the effect of a variable (factor) on the result by changing the level of the variable while keeping all other variables at a fixed level. This method can help researchers understand the contribution of each independent variable to the experimental result. OFAT method is easy to understand and implement because it only considers one variable at a time. By gradually changing one factor, its direct impact on the result can be observed and recorded. When analyzing a single factor, all other factors are controlled at a constant level to eliminate their interference.

[0111] Specifically, the effectiveness of dividing the WUI region within the experimental area is evaluated by three indicators: the number of buildings within the WUI, the number of wild fire ignition points within the WUI, and the percentage change in the area of the fire trace land and the change in the building risk index. In practice, when the percentage change of an indicator is less than the percentage change of the WUI components, the threshold can be considered stable. For example, for the risk index, when the threshold is less than 25, the number of buildings within the WUI and the number of wild fire ignition points within the WUI are relatively stable; for another example, when the threshold is less than 30, the change in the area of the fire trace land is relatively stable.

[0112] where the percentage change of the WUI components refers to the relative proportion or number of each component (such as the building area, vegetation area, etc.) that constitutes the WUI during the division of the forest-town interface (WUI). In WUI division and management, monitoring the percentage change of these components is crucial for understanding the dynamic changes of the region and developing appropriate risk management measures. By comparing the percentage change of these components with the percentage change of the number of buildings, the number of wild fire ignition points, and the area of the fire trace land, the stability and effectiveness of WUI division can be evaluated. If the changes in the number of buildings, the number of wild fire ignition points, and the area of the fire trace land are smaller than the changes in the WUI components, it can be considered that the current WUI division is relatively stable, as these key indicators have not fluctuated greatly due to minor changes within the WUI.

[0113] In this embodiment, a single-factor method is applied to verify the effectiveness of multiple forest-town interfaces within the region to be divided, systematically evaluating and verifying the impact of different factors on the effectiveness of WUI division, thereby providing more scientific decision support for wild fire risk management and WUI management, and improving the accuracy and reliability of WUI division.

[0114] In addition, in one possible implementation, after step 109, the above method further includes:

[0115] The multiple forest-town interfaces within the region to be divided are filled to divide the non-forest-town interfaces completely surrounded by the forest-town interfaces into forest-town interfaces.

[0116] In practical applications, geographic information systems (GIS) are used to identify non-WUI regions completely surrounded by WUI regions. Further, filling processing is applied to these completely surrounded non-WUI regions to reclassify them as WUI regions, and the boundaries of the WUI are updated to ensure that the newly divided regions are contained within the boundaries of the WUI.

[0117] In this embodiment, the multiple forest-town interface domains in the to-be-divided region are filled to divide the non-forest-town interface domains completely surrounded by the forest-town interface domains into forest-town interface domains, ensuring the continuity and integrity of the WUI region and improving the accuracy and reliability of WUI division.

[0118] In addition, in some embodiments, the WUI region is divided into three risk levels of low, medium and high based on the building wild fire risk index.

[0119] Further, for the forest-town interface domains of low, medium and high risks, population data, road data and infrastructure data can be further integrated, and the land use planning, building standards, and management and rescue activities of wild fires can be adjusted in cooperation with the wild fire management department for different risk levels, so as to ensure the timeliness of rescue activities and provide more scientific decision support. For example, by combining population density data with high, medium and low risk areas, it can be accurately determined which high population density areas need to be evacuated first; at the same time, road use and evacuation plans can be optimized to ensure smooth traffic in high-risk areas, facilitating the rapid deployment of emergency evacuation and rescue resources. In addition, for wild fire protection of different risk forest-town interface domains, building owners can also take the best combination of adaptive measures according to the vulnerability of buildings and wild fire exposure. Through such multi-dimensional integration, emergency management and resource allocation can be effectively guided, and ultimately the impact of wild fires can be reduced, providing local governments and communities with more scientific and systematic wild fire risk management tools and improving the safety and disaster response capabilities of towns.

[0120] In the WUI division method based on building wild fire risk provided in this embodiment, the to-be-divided region is divided according to a predetermined resolution to obtain multiple fuel grids, and the weighted fuel grade of each fuel grid is determined, so as to realize the risk level division of each fuel grid, which is beneficial to more fine management of wild fires. Further, based on the weighted fuel grade of each fuel grid, the building wild fire risk index of each house and the vegetation danger index of each fuel grid in the to-be-divided region are calculated, so as to realize risk quantification evaluation of each house and the vegetation around the house. Further, according to the building wild fire risk index and the vegetation danger index, risk houses and risk fuel grids corresponding to the risk houses are screened out, which is helpful to optimize the allocation of emergency resources and ensure quick and effective response in case of fire. Further, each risk house and each risk fuel grid corresponding to the risk house are regionally merged to obtain multiple forest-town interface domains in the to-be-divided region. Therefore, the scheme of this embodiment realizes fine and practical WUI division, improves the accuracy of WUI division, and provides more scientific and effective decision support for wild fire management.

[0121] The housing wild fire risk based WUI partition device provided by the present application is described below, and the housing wild fire risk based WUI partition device described below can be correspondingly referred to the housing wild fire risk based WUI partition method described above.

[0122] Figure 2 is a structural schematic diagram of the housing wild fire risk based WUI partition device provided by the present application, as Figure 2 shown, the housing wild fire risk based WUI partition device comprises a grid partition module 21, a first calculation module 22, a second calculation module 23, a first screening module 24, a second screening module 25, and a region merging module 26.

[0123] The grid partition module 21 is configured to partition the region to be partitioned according to a predetermined resolution, obtain a plurality of fuel grids, and determine the weighted fuel grade of each fuel grid.

[0124] The resolution refers to the spatial resolution of the land cover data when performing geographic information system (GIS) analysis. The spatial resolution refers to the size of the smallest unit in an image or data set, which determines the size of the smallest feature that can be identified. In geographic information systems, resolution is often used to describe the accuracy of raster data, that is, the actual ground area represented by each grid cell (pixel). In practice, resolution refers to the degree of spatial detail of the data, that is, the geographical range covered by each data point.

[0125] In practical applications, the grid partition module 21 partitions the region to be partitioned according to a predetermined resolution, and a plurality of area-equal grids can be obtained, including fuel grids and non-fuel grids. Further, the weighted fuel grade of each fuel grid is determined. For non-fuel grids, in this embodiment, the grid partition module 21 assigns the weighted fuel grade to a preset value, for example, assigns the weighted fuel grade to a preset value of 10.

[0126] Specifically, for each fuel grid, the grid partition module 21 considers the land cover type of the vegetation in the fuel grid and the horizontal fuel connectivity of the fuel grid, and comprehensively determines the weighted fuel grade of the fuel grid. It can be understood that the weighted fuel grade of each fuel grid comprehensively considers the land cover type and connectivity corresponding to the fuel grid, and provides important data support for subsequent wild fire risk assessment.

[0127] As an example, in a possible implementation, when the above-mentioned grid partition module 21 is used to determine the weighted fuel grade of each fuel grid, it is specifically used for:

[0128] According to the suppression difficulty of different land cover types, the cost weight value corresponding to different land cover types is determined;

[0129] calculate an aggregation index corresponding to each fuel grid;

[0130] For each fuel grid, determine the weighted fuel class of the fuel grid according to the cost weight value corresponding to the land cover type of the fuel grid and the aggregation index corresponding to the fuel grid.

[0131] wherein the suppression difficulty of the land cover type refers to the difficulty of fire suppression or control for a specific land cover type in wild fire management. Specifically, different types of vegetation have different combustion characteristics, some vegetation is easier to ignite, burns faster, or is more difficult to extinguish, so the suppression difficulty of different land cover types is different.

[0132] In practical applications, considering the differences in the degree of combustion and the speed of spread of different vegetation around the house when a wild fire occurs, different land cover types are ranked according to the suppression difficulty of different land cover types. Specifically, the embodiment adopts a variable width buffer technique to determine the cost weight value corresponding to different land cover types. The variable width buffer technique uses cost distance calculation to link different cost weights with land cover types in GlobeLand30-2020 to determine the cost weight corresponding to different land cover types.

[0133] Further, the horizontal fuel connectivity of each fuel grid is evaluated, i.e., the aggregation index corresponding to each fuel grid is calculated.

[0134] wherein the aggregation index (AI) provides a measure of the connectivity or degree of aggregation of fuel dispersed in the region, and it also provides a reference for the difficulty of fire spread in the entire landscape. For example, the aggregation index of all fuel grids in City A is calculated in a 5*5 moving window, and the calculation formula of the aggregation index is as follows:

[0135]

[0136] wherein, refers to the aggregation degree of the corresponding fuel class , i.e., the sum of the adjacent logarithms of all pixels of the same type within the 5x5 window.

[0137] Further, the aggregation index is classified simply, specifically, AI>90 is classified as "high aggregation" and assigned a value of 0; 0<AI ≤ 90 is "lower aggregation" and assigned a value of 1; AI = 0 is "no aggregation" and assigned a value of 2.

[0138] It can be understood that according to Table 1 above, for each fuel grid, according to the land cover type of the fuel grid, the cost weight value corresponding to the land cover type of the fuel grid can be determined.​

[0139] Further, for each fuel grid, a weighted fuel rank of the fuel grid is determined according to the cost weight value corresponding to the land cover type of the fuel grid and the aggregation index corresponding to the fuel grid. Specifically, for each fuel grid, the weighted fuel rank of the fuel grid is calculated by combining the cost weight value corresponding to the land cover type of the fuel grid and the aggregation index corresponding to the fuel grid. For example, the weighted fuel rank value of a fuel grid with a high aggregation index (AI value of 0) and a land cover type of open coniferous forest (rank of 1) is 1. The weighted fuel rank value of a non-fuel grid is assigned as 10.

[0140] It can be understood that for each fuel grid, a weighted fuel rank of the fuel grid is determined according to the cost weight value corresponding to the land cover type of the fuel grid and the aggregation index corresponding to the fuel grid. The calculation of the weighted fuel rank integrates the connectivity and suppression difficulty of the fuel, providing a more refined risk indicator for wild fire risk assessment and WUI division. This comprehensive assessment helps to identify areas with high fire risk and provides a scientific basis for developing effective fire prevention and response strategies.

[0141] In combination Figure 2 , the first calculation module 22 is configured to, for each house in the to-be-divided region, establish a buffer zone corresponding to the house, and calculate a building wild fire risk index of the house based on the weighted fuel rank of each fuel grid falling within the buffer zone corresponding to the house.

[0142] In practical applications, for each house in the to-be-divided region, a buffer zone corresponding to the house is established, which means that in a geographic information system (GIS), a virtual boundary region is created around each building. This region is usually a circular or polygonal region, centered on the building and extending a certain distance outward. This buffer zone is used to assess and quantify the wild fire risk of each individual house and its surrounding vegetation.

[0143] It can be understood that the buffer zone can be circular, square, or other polygonal, and the specific shape depends on the research needs and geographical features.

[0144] In an example, the buffer zone corresponding to the house is an annular buffer zone with a preset radius.

[0145] Specifically, the size of the buffer zone can be determined according to the research purpose and actual needs. For example, different levels of buffer zones can be set, such as 2400 meters, 1200 meters, 800 meters, etc.

[0146] Further, based on the building footprint data, the wild fire risk of each house is quantitatively analyzed, and the building wild fire risk index of each house is calculated to realize the evaluation of the specific wild fire risk of each house in the study area. This not only helps the managers to more intuitively and finely understand the distribution of the wild fire risk, but also provides a scientific basis for formulating targeted building fire prevention strategies and emergency plans.

[0147] As an example, in a possible implementation, the first calculation module 22 is configured to calculate the building wild fire risk index of the house based on the weighted fuel grade of each fuel grid falling within the buffer zone corresponding to the house, and specifically configured to:

[0148] According to the weighted fuel grade of each fuel grid falling within the buffer zone corresponding to the house and the buffer distance of each fuel grid, the influence fuel grid corresponding to the house is selected from all the fuel grids falling within the buffer zone corresponding to the house; wherein the buffer distance of the fuel grid is the distance between the fuel grid and the house;

[0149] According to the weighted fuel grade of each influence fuel grid corresponding to the house, the buffer distance, and the number of land cover types of the influence fuel grid corresponding to the house, the building wild fire risk index of the house is calculated.

[0150] Specifically, according to the buffer distance of each fuel grid, the buffer zone level corresponding to each grid can be determined, and further, it is determined whether the weighted fuel grade corresponding to each fuel grid is valid. If valid, the fuel grid with valid weighted fuel grade is taken as the influence fuel grid corresponding to the house.

[0151] Further, based on the influence of the fuel grade in different buffer zones around the building, the building wild fire risk index (BWRI) of each house is calculated. The lower the weighted fuel grade of the vegetation, the greater the potential risk, and at the same time, considering the distance from the dangerous vegetation to the house, the farther the distance, the smaller the risk.

[0152] Specifically, according to the weighted fuel grade of each influence fuel grid corresponding to the house, the buffer distance, and the number of land cover types of the influence fuel grid corresponding to the house, the building wild fire risk index of the house is calculated. As an example, the calculation formula of the building wild fire risk index is as follows:

[0153]

[0154] Wherein, b is the buffer zone level, f is the weighted fuel grade, and n is the number of land cover types of the influence fuel grid corresponding to the house.

[0155] In this embodiment, the building wild fire risk index of the building is calculated according to the weighted fuel class of each fuel grid corresponding to the building, the buffer distance, and the number of land cover types of the fuel grid corresponding to the building. This risk assessment method provides a specific assessment of the wild fire risk of buildings in different areas, which can help local governments and residents to take appropriate preventive measures, such as adding fire fighting facilities, improving vegetation management, or re-planning the layout of the area, to reduce the potential fire risk.

[0156] In combination Figure 2 , the second calculation module 23 is configured to, for each fuel grid, establish a buffer zone corresponding to the fuel grid, and calculate a vegetation danger index of the fuel grid based on the building risk value of each building falling within the buffer zone corresponding to the fuel grid.

[0157] When a wild fire occurs, a crucial factor is whether there is flammable vegetation around the building, which directly determines whether the wild fire can spread and spread. Therefore, it is particularly important to deeply explore and understand the spatial distribution of wild vegetation in the area and the fire risk posed by the adjacent building. In order to more accurately assess this risk, the present application further calculates the vegetation danger index (VDI) of the fuel grid on the basis of the building risk index. The vegetation danger index is used to measure the degree of wild vegetation threat to the surrounding buildings.

[0158] In order to facilitate calculation, in this embodiment, the land cover data (GlobeLand30-2020 data set) is first subjected to a grid conversion operation, and then a buffer zone corresponding to each grid point is established according to the weighted fuel grid class. Finally, all buildings falling within the buffer zone corresponding to the grid point (buildings falling within the buffer zone or having an overlapping part with the buffer zone) are counted, and the vegetation danger index of the fuel grid is calculated.

[0159] As an example, in one possible implementation, when the second calculation module 23 calculates the vegetation danger index of the fuel grid based on the building risk value of each building falling within the buffer zone corresponding to the fuel grid, it is specifically configured to:

[0160] count all buildings falling within the buffer zone corresponding to the fuel grid;

[0161] calculate the vegetation danger index of the fuel grid according to the building risk value of each building falling within the buffer zone corresponding to the fuel grid and the building area of each building.

[0162] By way of example, the calculation formula of the vegetation danger index is as follows:

[0163]

[0164] Wherein, BWRI is the building risk value of each house falling in the buffer zone corresponding to the fuel grid, and A represents the area of the house (unit: square meter). Considering that the product of the building danger index and the building area may have a huge difference in different grids, the application adopts a logarithmic processing method. This processing can effectively reduce the gap between data, making the risk level between different grids more comparable, so as to obtain a more balanced and easy-to-understand index.

[0165] In combination Figure 2 The first screening module 24 is configured to screen, from all houses in the region to be divided, houses with a building wild fire risk index greater than a preset first threshold value as risk houses.

[0166] The second screening module 25 is configured to, for each risk house, screen, from all fuel grids falling in the buffer zone corresponding to the risk house, a fuel grid with a vegetation danger index greater than a preset second threshold value as a risk fuel grid corresponding to the risk house.

[0167] The region merging module 26 is configured to, for each risk house, perform region merging on the risk house and the risk fuel grid corresponding to the risk house to obtain a plurality of forest-urban interface domains in the region to be divided.

[0168] In actual application, in order to reduce the risk of structure loss during a wild fire, the WUI division process first focuses on houses and then spreads outward from the houses. Specifically, the houses are preliminarily screened through the building risk index, and then the vegetation that has an influence on the houses is focused on, so that the region that is more likely to pose a threat to humans during a wild fire can be more scientifically divided.

[0169] It should be noted that the first threshold value and the second threshold value are preset according to the WUI region demand, and in actual application, the first threshold value and the second threshold value can be adjusted according to the actual WUI region demand. For example, the second threshold value can be 0, and the fuel grid with a vegetation danger index greater than 0 is taken as the risk fuel grid corresponding to the risk house.

[0170] In addition, in a possible implementation, the apparatus further includes:

[0171] The verification module is configured to apply a single-factor method to verify the effectiveness of the plurality of forest-urban interface domains in the region to be divided.

[0172] Among them, single factor method (OFAT) is an experimental design and analysis method, which studies the influence of a variable (factor) on the result by changing the level of the variable while keeping all other variables at a fixed level. This method can help researchers understand the contribution of each independent variable to the experimental result. OFAT method is easy to understand and implement, because it only considers one variable at a time. By changing one factor step by step, the direct effect of it on the result can be observed and recorded. When analyzing a single factor, all other factors are controlled at a constant level to eliminate their interference.

[0173] Specifically, the effectiveness of dividing the WUI area in the experimental area is evaluated by three indicators: the number of buildings in the WUI, the number of wild fire ignition points in the WUI, and the percentage change of the area of the fire trace land and the change of the building risk index. In practice, when the percentage change of the indicator is less than the percentage change of the WUI component, the threshold can be considered stable. For example, for the risk index, when the threshold is less than 25, the number of buildings in the WUI and the change of the wild fire ignition point in the WUI are relatively stable; for another example, when the threshold is less than 30, the change of the area of the fire trace land is relatively stable.

[0174] In this embodiment, the single factor method is applied to verify the effectiveness of the multiple forest-town interface domains in the region to be divided, systematically evaluating and verifying the influence of different factors on the effectiveness of WUI division, thereby providing more scientific decision support for wild fire risk management and WUI management, and improving the accuracy and reliability of WUI division.

[0175] In addition, in a possible implementation, the apparatus further includes:

[0176] The filling module is configured to perform filling processing on the multiple forest-town interface domains in the region to be divided, so as to divide the non-forest-town interface domains completely surrounded by the forest-town interface domains into forest-town interface domains.

[0177] In practical application, geographic information system (GIS) is applied to identify the non-WUI regions completely surrounded by the WUI region. Further, the filling processing is applied to the completely surrounded non-WUI regions, so as to reclassify them as WUI regions, and update the boundary of the WUI, to ensure that the newly divided regions are contained in the boundary of the WUI.

[0178] In this embodiment, the filling processing is performed on the multiple forest-town interface domains in the region to be divided, so as to divide the non-forest-town interface domains completely surrounded by the forest-town interface domains into forest-town interface domains, thereby ensuring the continuity and integrity of the WUI region, and improving the accuracy and reliability of the WUI division.

[0179] The WUI partitioning device based on house wild fire risk provided by the embodiment, the grid partitioning module divides the region to be partitioned according to a predetermined resolution, obtains a plurality of fuel grids, and determines the weighted fuel grade of each fuel grid, so that the risk grade of each fuel grid is distinguished, which is beneficial to the more fine management of wild fire; further, the first calculation module and the second calculation module calculate the building wild fire risk index of each house in the region to be partitioned and the vegetation danger index of each fuel grid based on the weighted fuel grade of each fuel grid, so that the risk quantification evaluation of each house and the vegetation around the house is realized; further, the first screening module and the second screening module screen out the risk house and the risk fuel grid corresponding to the risk house according to the building wild fire risk index and the vegetation danger index, which is helpful to optimize the allocation of emergency resources and ensure that the response can be quickly and effectively made when the fire occurs. Further, the region merging module merges the region of each risk house and the risk fuel grid corresponding to each risk house, and obtains a plurality of forest town junction domains in the region to be partitioned. Therefore, the scheme of the embodiment realizes fine and practical WUI partitioning, improves the accuracy of WUI partitioning, and provides more scientific and effective decision support for wild fire management.

[0180] Figure 3 is a structural schematic diagram of an electronic device provided by the present application, like Figure 3As shown, the electronic device can include a processor 310, a communications interface 320, a memory 330, and a communications bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communications bus 340. The processor 310 can invoke the logic instructions in the memory 330 to execute the WUI division method based on the house wild fire risk, which includes: dividing the to-be-divided region according to a predetermined resolution to obtain a plurality of fuel grids, and determining a weighted fuel grade of each fuel grid; for each house in the to-be-divided region, establishing a buffer zone corresponding to the house, and based on the weighted fuel grade of each fuel grid falling within the buffer zone corresponding to the house, calculating a building wild fire risk index of the house; for each fuel grid, establishing a buffer zone corresponding to the fuel grid, and based on the building risk value of each house falling within the buffer zone corresponding to the fuel grid, calculating a vegetation danger index of the fuel grid; from all the houses in the to-be-divided region, screening out houses with a building wild fire risk index greater than a preset first threshold value as risk houses; for each risk house, from all the fuel grids falling within the buffer zone corresponding to the risk house, screening out fuel grids with a vegetation danger index greater than a preset second threshold value as risk fuel grids corresponding to the risk house; and for each risk house, performing region merging on the risk house and the risk fuel grids corresponding to the risk house to obtain a plurality of forest-town interface domains in the to-be-divided region.

[0181] In addition, the logic instructions in the memory 330 described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0182] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a non-transitory computer-readable storage medium, and the computer program can be executed by a processor to enable a computer to perform the WUI division method based on house wild fire risk provided by the above-mentioned methods, which comprises: dividing the region to be divided according to a predetermined resolution to obtain a plurality of fuel grids, and determining the weighted fuel grade of each fuel grid; for each house in the region to be divided, establishing a buffer zone corresponding to the house, and based on the weighted fuel grade of each fuel grid falling within the buffer zone corresponding to the house, calculating the building wild fire risk index of the house; for each fuel grid, establishing a buffer zone corresponding to the fuel grid, and based on the building risk value of each house falling within the buffer zone corresponding to the fuel grid, calculating the vegetation danger index of the fuel grid; from all the houses in the region to be divided, screening out the houses with building wild fire risk index greater than a preset first threshold value as risk houses; for each risk house, from all the fuel grids falling within the buffer zone corresponding to the risk house, screening out the fuel grids with vegetation danger index greater than a preset second threshold value as risk fuel grids corresponding to the risk house; and for each risk house, performing region merging on the risk house and the risk fuel grids corresponding to the risk house to obtain a plurality of forest-town interface domains in the region to be divided.

[0183] In another aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and the computer program can be executed by a processor to implement the WUI division method based on house wild fire risk provided by the above-mentioned methods, which comprises: dividing the region to be divided according to a predetermined resolution to obtain a plurality of fuel grids, and determining the weighted fuel grade of each fuel grid; for each house in the region to be divided, establishing a buffer zone corresponding to the house, and based on the weighted fuel grade of each fuel grid falling within the buffer zone corresponding to the house, calculating the building wild fire risk index of the house; for each fuel grid, establishing a buffer zone corresponding to the fuel grid, and based on the building risk value of each house falling within the buffer zone corresponding to the fuel grid, calculating the vegetation danger index of the fuel grid; from all the houses in the region to be divided, screening out the houses with building wild fire risk index greater than a preset first threshold value as risk houses; for each risk house, from all the fuel grids falling within the buffer zone corresponding to the risk house, screening out the fuel grids with vegetation danger index greater than a preset second threshold value as risk fuel grids corresponding to the risk house; and for each risk house, performing region merging on the risk house and the risk fuel grids corresponding to the risk house to obtain a plurality of forest-town interface domains in the region to be divided.

[0184] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0185] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0186] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A WUI classification method based on house wildfire risk, characterized in that, include: The area to be divided is divided according to a predetermined resolution to obtain multiple fuel grids, and the weighted fuel level of each fuel grid is determined. For each house in the area to be divided, a buffer zone is established for the house, and the building wildfire risk index of the house is calculated based on the weighted fuel level of each fuel grid falling within the buffer zone. For each fuel grid, a buffer zone corresponding to the fuel grid is established, and the vegetation hazard index of the fuel grid is calculated based on the building risk value of each house falling within the buffer zone corresponding to the fuel grid. From all the houses in the area to be divided, houses with a wildfire risk index greater than a preset first threshold are selected as high-risk houses; For each risky house, from all fuel grids falling within the buffer zone corresponding to the risky house, select fuel grids with a vegetation hazard index greater than a preset second threshold as the risky fuel grids corresponding to the risky house. For each risky house, the risky house and the risky fuel grid corresponding to the risky house are merged into a region to obtain multiple forest town boundary areas within the area to be divided.

2. The WUI classification method for wildfire risk assessment of houses according to claim 1, characterized in that, The determination of the weighted fuel grade for each fuel grid includes: Based on the difficulty of suppressing different land cover types, determine the cost weight values ​​corresponding to different land cover types; Calculate the polymerization index for each fuel grid; For each fuel grid, the weighted fuel class of the fuel grid is determined based on the cost weight value corresponding to the land cover type of the fuel grid and the aggregation index corresponding to the fuel grid.

3. The WUI classification method for wildfire risk assessment of houses according to claim 1, characterized in that, The calculation of the building wildfire risk index based on the weighted fuel level of each fuel grid falling within the buffer zone corresponding to the building includes: Based on the weighted fuel grade of each fuel grid falling within the buffer zone corresponding to the house and the buffer distance of each fuel grid, the influencing fuel grid corresponding to the house is obtained from all fuel grids falling within the buffer zone corresponding to the house; wherein, the buffer distance of the fuel grid is the distance between the fuel grid and the house; The building wildfire risk index of the building is calculated based on the weighted fuel grade, buffer distance, and number of land cover types of each affected fuel grid corresponding to the building.

4. The WUI classification method for wildfire risk assessment of houses according to claim 1, characterized in that, The calculation of the vegetation hazard index of the fuel grid based on the building risk value of each house falling within the buffer zone corresponding to the fuel grid includes: Count all houses that fall within the buffer zone corresponding to the fuel grid; The vegetation hazard index of the fuel grid is calculated based on the building risk value and building area of ​​each house falling within the buffer zone corresponding to the fuel grid.

5. The WUI classification method for wildfire risk assessment of houses according to claim 1, characterized in that, The buffer zone corresponding to the house is a ring-shaped buffer zone with a preset radius.

6. The WUI classification method for wildfire risk assessment of houses according to any one of claims 1-5, characterized in that, For each risky house, after merging the risky house and its corresponding risky fuel grid to obtain multiple forest town boundary areas within the area to be divided, the method further includes: The effectiveness of the multiple forest town boundary areas within the region to be delineated was verified by applying a single-factor method.

7. The WUI classification method for wildfire risk assessment of houses according to any one of claims 1-5, characterized in that, For each risky house, after merging the risky house and its corresponding risky fuel grid to obtain multiple forest town boundary areas within the area to be divided, the method further includes: The boundary areas of multiple forest towns within the area to be divided are filled to divide the non-forest town boundary areas that are completely surrounded by the forest town boundary areas into forest town boundary areas.

8. A WUI (Wildfire Risk Assessment) device based on house wildfire risk, characterized in that, include: The grid division module is used to divide the area to be divided according to a predetermined resolution to obtain multiple fuel grids and determine the weighted fuel grade of each fuel grid. The first calculation module is used to establish a buffer zone corresponding to each house in the area to be divided, and to calculate the building wildfire risk index of the house based on the weighted fuel level of each fuel grid falling in the buffer zone corresponding to the house. The second calculation module is used to establish a buffer zone corresponding to each fuel grid and calculate the vegetation hazard index of the fuel grid based on the building risk value of each house falling within the buffer zone corresponding to the fuel grid. The first screening module is used to screen out houses from all houses in the area to be divided that have a wildfire risk index greater than a preset first threshold, and these houses are designated as high-risk houses. The second screening module is used to select, for each risky house, fuel grids whose vegetation hazard index is greater than a preset second threshold from all fuel grids falling within the buffer zone corresponding to the risky house, and use them as the risky fuel grids corresponding to the risky house. The region merging module is used to merge the risky house and the risky fuel grid corresponding to the risky house for each risky house, so as to obtain multiple forest town boundary areas within the area to be divided.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the WUI classification method based on house wildfire risk as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the WUI classification method based on house wildfire risk as described in any one of claims 1 to 7.

Images