Avalanche disaster risk method, system, device and medium

Abstract

The invention provides an avalanche disaster risk method, system and device and a medium, and relates to the technical field of avalanche disaster response and prevention. The method comprises the following steps: acquiring avalanche occurrence data and disaster-pregnancy background data of a target area, and determining avalanche disaster-pregnancy factors according to the disaster-pregnancy background data; based on the avalanche occurrence data of the target area, taking an avalanche point as a positive sample, collecting a non-avalanche point as a negative sample, constructing training data, constructing a random forest model, and training the random forest model by using the training data to obtain an avalanche dynamic evaluation model; and based on the avalanche dynamic evaluation model, evaluating the avalanche disaster risk of the target area. The problem of how to obtain a dynamic avalanche risk assessment model by focusing on the change of meteorological factors in the snow season avalanche high-incidence period and provide key factors needing to be monitored for avalanche early warning in different months of the snow season is solved.

Description

Technical Field

[0001] This application relates to the technical field of avalanche disaster response and prevention, and particularly relates to an avalanche disaster risk method, system, device and medium. Background Art

[0002] An avalanche is a major natural disaster in mountainous areas covered by snow, which can quickly destroy vegetation, infrastructure and transportation lines, cause casualties and property losses, and pose a serious threat to social stability and sustainable development. However, traditional avalanche risk area identification mainly relies on field investigations and remote sensing technologies, but these methods have limitations in identifying avalanche coverage and identification efficiency. Among them, ground surveys usually rely on expert experience. By conducting on-site surveys, the snow layer structure and terrain features are understood to evaluate avalanche risks. Although this method is accurate, it consumes huge human resources and time, and the coverage is very limited. Remote sensing technology can obtain data through means such as satellite images and aerial photography, and detailed avalanche information can be obtained even in inaccessible areas; however, remote sensing data lacks certain data reliability and availability, which will hinder avalanche forecasting services, and factors such as slope, insufficient light, bad weather conditions and overexposure of images will all affect the quality of optical remote sensing images. Moreover, considering the strong time difference of meteorological factors, it further increases the difficulty of traditional methods including remote sensing interpretation, making it difficult to obtain the dynamic change characteristics of avalanche risks and bringing challenges to the accurate prevention and control of avalanche disasters. Therefore, how to quickly identify the avalanche risks in complex mountainous terrains and their dynamic changes is a key problem that needs to be solved urgently at present. Summary of the Invention

[0003] This application provides an avalanche disaster risk method, system, device and medium to solve the technical problem of how to focus on the changes of meteorological factors during the high-incidence period of avalanches in the snow season, obtain a dynamic avalanche risk assessment model, and propose factors that need to be monitored key for avalanche warnings in different months of the snow season.

[0004] In a first aspect, this application provides an avalanche disaster risk method, including: Obtain the avalanche occurrence data and disaster-forming background data of the target area, and determine the avalanche disaster-forming factors according to the disaster-forming background data; Based on the avalanche occurrence data of the target area, taking avalanche points as positive samples, collecting non-avalanche points as negative samples according to the ratio of 1:1 with the positive samples, constructing training data, constructing a random forest model, and using the training data to train the random forest model. During training, taking avalanche points as the labels of training samples and avalanche disaster-forming factors as the input features of the random forest model, and determining the factor weights according to the splitting contribution degree of the input features on the decision tree of the random forest model to obtain an avalanche dynamic assessment model; Based on the avalanche dynamic assessment model, evaluate the avalanche disaster risk of the target area.

[0005] In a possible design, the disaster-forming background data includes remote sensing image data of the target area, elevation DEM data, river distribution vector data, monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed raster data corresponding to the snow season.

[0006] In a possible design, determine the avalanche disaster-forming factors according to the disaster-forming background data, including: Calculate the bands of the remote sensing image data of the target area, extract the normalized difference vegetation index value, resample the data to the target resolution, and obtain the factor NDVI. Based on the river distribution vector data, set an interval distance adapted to the size of the target area to obtain buffer layers at different distances from the river, convert the vector data to raster data, and resample the data to the target resolution to obtain the factor distance from the river D. Resample the elevation DEM data to the target resolution to obtain the factor elevation Dem.

[0007] Based on the DEM data at the target resolution, obtain the factor slope Slope at the target resolution. Based on the DEM data at the target resolution, obtain the factor curvature Cur at the target resolution. Based on the DEM data at the target resolution, extract the maximum and minimum values of the elevation in a circular area with a set radius, and find the difference to obtain the factor terrain undulation degree Ula at the target resolution. Based on the DEM data at the target resolution, calculate the standard deviation and mean of the DEM, and find the ratio of the DEM standard deviation to the DEM mean to obtain the factor elevation coefficient of variation Var at the target resolution.

[0008] Resample the monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed raster data to the target resolution to obtain the factors monthly average snow cover Cov, monthly average snow depth Sdp, monthly average snowfall Sf, and monthly average wind speed Wind at the target resolution.

[0009] In a possible design, the avalanche disaster-forming factors include NDVI, distance from the river, elevation, slope, curvature, terrain undulation degree, elevation coefficient of variation, monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed.

[0010] In a possible design, the avalanche dynamic assessment model is expressed as: ; ; ; ; ; ; wherein, are the avalanche susceptibility index values for January, February, March, April, May, and December respectively; , , , , , , , , , , are the normalized elevation, slope, curvature, topographic relief, distance from river, coefficient of variation of factor elevation, NDVI, average monthly snowfall in the nth month, average monthly snow depth in the nth month, average monthly snow cover in the nth month, and average monthly wind speed in the nth month respectively, where n = 1, 2, 3, 4, 5, 12.

[0011] In a possible design, based on the avalanche dynamic assessment model, the avalanche disaster risk of the target area is evaluated: Obtain the real-time disaster-forming background data of the target area, and determine the avalanche disaster-forming factors based on the real-time disaster-forming background data; Normalize the avalanche disaster-forming factors to obtain the normalized avalanche disaster-forming factors; Substitute the normalized avalanche disaster-forming factors into the avalanche dynamic assessment model to obtain the avalanche susceptibility index value; Based on the avalanche susceptibility index value, establish an avalanche susceptibility index distribution map of the target area to evaluate the avalanche disaster risk of the target area.

[0012] In a possible design, the avalanche disaster-forming factors are normalized by the following formula to obtain the normalized avalanche disaster-forming factors: ; wherein, Dem represents elevation, Dem max is the maximum elevation; Slope represents slope, Slope max is the maximum slope; Cur represents curvature, Cur max is the maximum curvature; Ula represents topographic relief, Ula max is the maximum topographic relief; Var represents the coefficient of variation of elevation, Var max is the maximum coefficient of variation of elevation; D represents the distance from the river, D max is the maximum distance from the river; NDVI represents the normalized difference vegetation index, NDVImax is the maximum value of the normalized difference vegetation index; Sf represents the snowfall, and Sf max is the maximum value of the snowfall; Sdp represents the snow depth, and Sdp max is the maximum value of the snow depth; Cov represents the snow cover, and Cov max is the maximum value of the snow cover; Wind represents the wind speed, and Wind max is the maximum value of the wind speed.

[0013] In a second aspect, the present application provides an avalanche disaster risk system, which includes a controller configured to: A data preprocessing module, configured to obtain avalanche occurrence data and disaster-forming background data of a target area, and determine avalanche disaster-forming factors according to the disaster-forming background data; A model training module, configured to, based on the avalanche occurrence data of the target area, use avalanche points as positive samples, collect non-avalanche points as negative samples according to a ratio of 1:1 with the positive samples to construct training data, construct a random forest model, and use the training data to train the random forest model. During training, use avalanche points as the labels of the training samples, use avalanche disaster-forming factors as the input features of the random forest model, and determine factor weights according to the splitting contribution degree of the input features on the decision tree of the random forest model to obtain an avalanche dynamic assessment model; A risk assessment module, configured to evaluate the avalanche disaster risk of the target area based on the avalanche dynamic assessment model.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, including: at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the avalanche disaster risk method as described in the first aspect and various possible designs of the first aspect above.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the avalanche disaster risk method as described in the first aspect and various possible designs of the first aspect above is implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the avalanche disaster risk method as described in the first aspect and various possible designs of the first aspect above is implemented.

[0017] The avalanche disaster risk method, system, device, and medium provided by the present application have at least the following beneficial effects: Through refined modeling strategies, this application accurately determines the weight coefficients of meteorological factors in different months, thereby achieving more accurate and reliable prediction of avalanches, providing strong technical support and decision-making basis for seasonal forecasting and early warning of avalanche disasters, effectively reducing avalanche disaster risks, and ensuring the safety of life and property and the stability of the ecological environment in relevant areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0019] Figure 1 It is a complete flowchart of a method for avalanche disaster risk provided by an embodiment of this application; Figure 2 It is a specific implementation flowchart of a method for avalanche disaster risk provided by an embodiment of this application; Figure 3 It is a structural diagram of a brain-like control network provided by an embodiment of this application.

[0020] Through the above drawings, specific embodiments of this application have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. On the contrary, they are merely examples of systems and methods consistent with some aspects of this application as detailed in the appended claims.

[0022] In the technical solution of this application, the collection, storage, use, processing, transmission, provision, and disclosure of information such as financial data or user data comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0023] It should be noted that in the embodiments of this application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned. They should be regarded as exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solution of this application, but it does not mean that the applicant has already or necessarily used this solution.

[0024] The following uses specific embodiments to elaborate in detail on the technical solution of the present application and how the technical solution of the present application solves the above technical problems. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0025] An embodiment of the present application provides an avalanche disaster risk method. As Figure 1 shown, it shows the complete process of the avalanche disaster risk method. First, perform factor correlation analysis based on avalanche monitoring data and disaster-causing factor data, and determine evaluation factors in combination with the snow avalanche database (with data for different months); then extract training samples from the snow avalanche database and divide them into a training set and a test set, and construct a dynamic evaluation model through a machine learning algorithm; the model comprehensively considers the factor weight differences in different months, and finally generates avalanche warning focus factors and a monthly dynamic avalanche susceptibility evaluation map.

[0026] As Figure 2 shown, it is a specific implementation flowchart of an avalanche disaster risk method provided by an embodiment of the present application. This avalanche disaster risk method can be implemented through the following steps S100 - S300.

[0027] S100: Obtain the avalanche occurrence data and disaster-causing background data of the target area, and determine the avalanche disaster-causing factors according to the disaster-causing background data.

[0028] The purpose of step S100 is to collect and process the data related to avalanche disaster risk, and thus provide the corresponding data basis for the model training in the subsequent step S200.

[0029] In some embodiments, step S100 can be implemented through the following steps S101 - S110.

[0030] S101: Collect the avalanche occurrence data of the target area.

[0031] S102: Collect the disaster-causing background data of the target area, including the remote sensing image data of the target area, elevation DEM data, river distribution vector data, and the monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed raster data corresponding to the snow season (January, February, March, April, May, December).

[0032] S103: Calculate the bands of the remote sensing image data of the target area and extract the normalized difference vegetation index NDVI value. Calculation formula: (NIR - R) / (NIR + R), where NIR is the reflection value of the near-infrared band and R is the reflection value of the red light band. The calculation result is between -1 and 1, and the closer the NDVI value is to 1, the higher the vegetation coverage. Resample the data to a resolution of 30m to obtain the factor NDVI.

[0033] S104: Apply the river vector data of the target area, use the "multiple range buffer" tool in ArcGIS to select an interval distance suitable for the size of the target area, obtain buffer layers at different distances from the river, convert the vector data into raster data, resample the data to a resolution of 30m, and obtain the factor distance from the river D.

[0034] S105: Resample the elevation DEM data to a resolution of 30m to obtain the factor elevation Dem.

[0035] S106: Apply the "slope" tool in ArcGIS, input the DEM data with a resolution of 30m, and obtain the factor slope Slope with a resolution of 30m.

[0036] S107: Apply the "curvature" tool in ArcGIS, input the DEM data with a resolution of 30m, and obtain the factor curvature Cur with a resolution of 30m.

[0037] S108: Through the "Focal Statistics" tool in ArcGIS software, input the DEM data with a resolution of 30m, extract the maximum and minimum values of the elevation in a circular area with a radius of 1000m, and then use the "Raster Calculator" tool to find the difference to obtain the factor terrain undulation degree Ula with a resolution of 30m.

[0038] S109: Elevation coefficient of variation = standard deviation of DEM / mean of DEM. Through the "Focal Statistics" tool in ArcGIS software, input the DEM data with a resolution of 30m, calculate the standard deviation of DEM and the mean of DEM, and then use the "Raster Calculator" tool to find the ratio to obtain the factor elevation coefficient of variation Var with a resolution of 30m.

[0039] S110: Apply the "resample" tool in ArcGIS to resample the monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed raster data to a resolution of 30m to obtain the factors monthly average snow cover Cov, monthly average snow depth Sdp, monthly average snowfall Sf, and monthly average wind speed Wind (January, February, March, April, May, December) with a resolution of 30m.

[0040] S200: Based on the avalanche occurrence data of the target area, taking the avalanche points as positive samples, collecting non-avalanche points as negative samples according to the ratio of 1:1 with the positive samples, constructing training data, constructing a random forest model, training the random forest model with the training data. During training, taking the avalanche points as the labels of the training samples, and the avalanche disaster-inducing factors as the input features of the random forest model, determining the factor weights according to the splitting contribution degree of the input features on the decision tree of the random forest model, and obtaining the avalanche dynamic assessment model.

[0041] Step S200 is the process of establishing an avalanche dynamic assessment model based on the random forest algorithm.

[0042] In some embodiments, step S200 can be implemented through the following steps S201 - S205.

[0043] S201: Combining the random forest algorithm, using the Google Earth Engine (GEE) platform for model training, taking the avalanche points as positive samples, collecting non-avalanche points as negative samples according to the ratio of 1:1 with the positive samples, constructing training data. Divide the training data into a training set and a test set according to the ratio of 7:3.

[0044] S202: Random forest is an ensemble learning method that makes predictions by combining multiple decision trees, iteratively calculating to determine that the number of decision trees is 15. Each decision tree is trained based on different random subsets, and finally the final result is obtained by voting or taking the average.

[0045] S203: Taking the avalanche points as the labels of the training samples, and taking NDVI, distance to the river, elevation, slope, curvature, terrain undulation degree, elevation coefficient of variation, monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed as feature inputs.

[0046] S204: Calculate the factor weights obtained by the model according to the splitting contribution degree of the features on the decision tree nodes.

[0047] S205: Obtain the avalanche dynamic assessment model according to the obtained factor weights.

[0048] In an exemplary embodiment, the avalanche dynamic assessment model is expressed as: ; ; ; ; ; ; Wherein, The avalanche susceptibility index values for January, February, March, April, May, and December respectively; , , , , , , , , , , The normalized elevation, slope, curvature, topographic relief, distance from the river, factor elevation coefficient of variation, NDVI, average monthly snowfall in the nth month, average monthly snow depth in the nth month, average monthly snow cover in the nth month, and average monthly wind speed in the nth month respectively, where n = 1, 2, 3, 4, 5, 12.

[0049] S300: Based on the avalanche dynamic assessment model, evaluate the avalanche disaster risk of the target area.

[0050] In some embodiments, step S300 can be implemented through the following steps S301 - S304.

[0051] S301: Obtain the real - time disaster - forming background data of the target area, and determine the avalanche disaster - forming factors based on the real - time disaster - forming background data.

[0052] It should be noted that the method for determining the avalanche disaster - forming factors is the same as that used in step S100, so it will not be elaborated here.

[0053] S302: Normalize the avalanche disaster - forming factors to obtain the normalized avalanche disaster - forming factors.

[0054] In some embodiments, the avalanche disaster - forming factors are normalized through the following formula to obtain the normalized avalanche disaster - forming factors: ; In the formula, Dem represents elevation, Dem max is the maximum elevation; Slope represents slope, Slope max is the maximum slope; Cur represents curvature, Cur max is the maximum curvature; Ula represents topographic relief, Ula max is the maximum topographic relief; Var represents the factor elevation coefficient of variation, Var max is the maximum factor elevation coefficient of variation; D represents the distance from the river, D max is the maximum distance from the river; NDVI represents the normalized difference vegetation index, NDVI max is the maximum normalized difference vegetation index; Sf represents snowfall, Sf max is the maximum snowfall; Sdp represents snow depth, Sdpmax is the maximum snow depth; Cov represents snow cover, Cov max is the maximum snow cover; Wind represents wind speed, Wind max is the maximum wind speed.

[0055] S303: Apply the "Raster Calculator" tool in ArcGIS to calculate each month's factor raster layer using the corresponding month's model to obtain the avalanche susceptibility index value (ASI).

[0056] S303: Obtain the avalanche susceptibility index distribution map of the target area from the avalanche susceptibility index value (ASI) to evaluate the avalanche disaster risk of the target area.

[0057] The embodiment of the present application also provides an avalanche disaster risk system, as Figure 3 shown. This avalanche disaster risk system includes: A data preprocessing module 401, configured to obtain the avalanche occurrence data and disaster-forming background data of the target area, and determine the avalanche disaster-forming factors according to the disaster-forming background data; A model training module 402, configured to, based on the avalanche occurrence data of the target area, use the avalanche points as positive samples, collect non-avalanche points as negative samples according to a ratio of 1:1 with the positive samples to construct training data, construct a random forest model, and use the training data to train the random forest model. During training, use the avalanche points as the labels of the training samples and the avalanche disaster-forming factors as the input features of the random forest model, and determine the factor weights according to the splitting contribution degree of the input features on the decision tree of the random forest model to obtain an avalanche dynamic assessment model; A risk assessment module 403, configured to evaluate the avalanche disaster risk of the target area based on the avalanche dynamic assessment model.

[0058] In some embodiments, the disaster-forming background data includes the remote sensing image data of the target area, elevation DEM data, river distribution vector data, monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed raster data corresponding to the snow season.

[0059] In some embodiments, the data preprocessing module is further configured to: Calculate the bands of the remote sensing image data of the target area, extract the normalized vegetation index value, and resample the data to the target resolution to obtain the factor NDVI; Based on the river distribution vector data, set an interval distance adapted to the size of the target area to obtain a buffer layer at different distances from the river, convert the vector data to raster data, and resample the data to the target resolution to obtain the factor distance from the river D; Resample the elevation DEM data to the target resolution to obtain the factor elevation Dem.

[0060] Based on the DEM data at the target resolution, obtain the factor slope Slope at the target resolution; Based on the DEM data at the target resolution, obtain the factor curvature Cur at the target resolution; Based on the DEM data at the target resolution, extract the maximum and minimum values of the elevation in a circular area with a set radius, and find the difference to obtain the factor terrain undulation degree Ula at the target resolution; Based on the DEM data at the target resolution, calculate the DEM standard deviation and the DEM mean, and find the ratio of the DEM standard deviation to the DEM mean to obtain the factor elevation variation coefficient Var at the target resolution.

[0061] Resample the monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed raster data to the target resolution to obtain the factor monthly average snow cover Cov, monthly average snow depth Sdp, monthly average snowfall Sf, and monthly average wind speed Wind at the target resolution.

[0062] In some embodiments, the avalanche disaster-forming factors include NDVI, distance to the river, elevation, slope, curvature, terrain undulation degree, elevation variation coefficient, monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed.

[0063] In some embodiments, the avalanche dynamic assessment model is expressed as: ; ; ; ; ; ; In the formula, are the avalanche susceptibility index values for January, February, March, April, May, and December respectively; , , , , , , , , , , They are the normalized elevation, slope, curvature, terrain undulation, distance to river, factor elevation coefficient of variation, NDVI, average monthly snowfall in the nth month, average monthly snow depth in the nth month, average monthly snow cover in the nth month, and average monthly wind speed in the nth month, where n = 1, 2, 3, 4, 5, 12.

[0064] In some embodiments, the risk assessment module is further configured to: Obtain real-time disaster-forming background data of the target area, and determine avalanche disaster-forming factors based on the real-time disaster-forming background data; Normalize the avalanche disaster-forming factors to obtain normalized avalanche disaster-forming factors; Substitute the normalized avalanche disaster-forming factors into the avalanche dynamic assessment model to obtain an avalanche susceptibility index value; Based on the avalanche susceptibility index value, establish an avalanche susceptibility index distribution map of the target area to evaluate the avalanche disaster risk of the target area.

[0065] In some embodiments, the risk assessment module is further configured to normalize the avalanche disaster-forming factors through the following formula to obtain normalized avalanche disaster-forming factors: ; In the formula, Dem represents elevation, and Dem max is the maximum elevation; Slope represents slope, and Slope max is the maximum slope; Cur represents curvature, and Cur max is the maximum curvature; Ula represents terrain undulation, and Ula max is the maximum terrain undulation; Var represents the factor elevation coefficient of variation, and Var max is the maximum factor elevation coefficient of variation; D represents the distance to river, and D max is the maximum distance to river; NDVI represents the normalized difference vegetation index, and NDVI max is the maximum normalized difference vegetation index; Sf represents snowfall, and Sf max is the maximum snowfall; Sdp represents snow depth, and Sdp max is the maximum snow depth; Cov represents snow cover, and Cov max is the maximum snow cover; Wind represents wind speed, and Wind max is the maximum wind speed.

[0066] An embodiment of the present application provides an electronic device. The electronic device may include: a processor and a memory, wherein the processor and the memory may communicate; exemplarily, the processor and the memory communicate through a communication bus.

[0067] The processor executes computer-executable instructions stored in the memory, enabling the processor to execute the solutions in the above embodiments. The processor may be a general-purpose processor, including a Central Processing Unit (CPU), a network processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0068] The communication bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. The transceiver is used to implement communication between the database access system and other computers (such as clients, read-write libraries, and read-only libraries). The memory may include Random Access Memory (RAM) and may also include non-volatile memory.

[0069] The electronic device provided in the embodiments of this application may be the terminal device in the above embodiments.

[0070] The embodiments of this application also provide a computer-readable storage medium storing computer instructions, which, when run on a computer, cause the computer to execute the technical solutions of the avalanche disaster risk method in the above embodiments.

[0071] The embodiments of this application also provide a computer program product including a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when at least one processor executes the computer program, it can implement the technical solutions of the avalanche disaster risk method in the above embodiments.

[0072] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of systems or modules can be in electrical, mechanical or other forms.

[0073] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to implement the solution of this embodiment.

[0074] In addition, in each embodiment of the present application, the functional modules can be integrated in a processing unit, or each module can exist physically alone, or two or more modules can be integrated in a unit. The units formed by the above modules can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0075] The integrated modules implemented in the form of software functional modules can be stored in a computer-readable storage medium. The above software functional modules are stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute some steps of the methods in various embodiments of the present application.

[0076] It should be understood that the above processor can be a central processing unit (Central Processing Unit, abbreviated as CPU), and can also be other general-purpose processors, digital signal processors (Digital Signal Processor, abbreviated as DSP), application specific integrated circuits (Application Specific Integrated Circuit, abbreviated as ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly implemented by the execution of the hardware processor, or can be implemented by the combination of the hardware and software modules in the processor.

[0077] The memory may include high-speed RAM memory, and may also include non-volatile storage NVM, such as at least one disk memory, and can also be a USB flash drive, a mobile hard disk, a read-only memory, a disk or an optical disc, etc.

[0078] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0079] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk or an optical disc. The storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0080] An exemplary storage medium is coupled to the processor, enabling the processor to read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic control unit or a master control device.

[0081] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disks or optical discs that can store program codes.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for avalanche disaster risk, characterized in that, The method includes: Obtaining the avalanche occurrence data and disaster-forming background data of the target area, and determining the avalanche disaster-forming factors according to the disaster-forming background data; Based on the avalanche occurrence data of the target area, taking the avalanche points as positive samples, collecting non-avalanche points as negative samples according to the ratio of 1:1 with the positive samples to construct training data, constructing a random forest model, training the random forest model with the training data. During training, taking the avalanche points as the labels of the training samples and the avalanche disaster-forming factors as the input features of the random forest model, and determining the factor weights according to the splitting contribution degree of the input features on the decision tree of the random forest model to obtain an avalanche dynamic assessment model; Based on the avalanche dynamic assessment model, assessing the avalanche disaster risk of the target area.

2. The avalanche disaster risk method according to claim 1, wherein The disaster-forming background data includes remote sensing image data of the target area, elevation DEM data, river distribution vector data, monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed raster data corresponding to the snow season.

3. The avalanche disaster risk method according to claim 2, wherein Determining the avalanche disaster-forming factors according to the disaster-forming background data includes: Calculating the bands of the remote sensing image data of the target area, extracting the normalized difference vegetation index value, and resampling the data to the target resolution to obtain the factor NDVI; Based on the river distribution vector data, setting an interval distance suitable for the size of the target area to obtain buffer layers at different distances from the river, converting the vector data into raster data, and resampling the data to the target resolution to obtain the factor distance from the river D; Resampling the elevation DEM data to the target resolution to obtain the factor elevation Dem; Based on the DEM data at the target resolution, obtaining the factor slope Slope at the target resolution; Based on the DEM data at the target resolution, obtaining the factor curvature Cur at the target resolution; Based on the DEM data at the target resolution, extracting the maximum and minimum values of the elevation in a circular area with a set radius, and finding the difference to obtain the factor terrain undulation degree Ula at the target resolution; Based on the DEM data at the target resolution, calculating the standard deviation and mean of the DEM, and finding the ratio of the standard deviation to the mean of the DEM to obtain the factor elevation coefficient of variation Var at the target resolution; Resampling the monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed raster data to the target resolution to obtain the factor monthly average snow cover Cov, monthly average snow depth Sdp, monthly average snowfall Sf, and monthly average wind speed Wind at the target resolution.

4. The avalanche disaster risk method according to claim 1, wherein The avalanche disaster-forming factors include NDVI, distance from the river, elevation, slope, curvature, terrain undulation degree, elevation coefficient of variation, monthly average snow cover, monthly average snow depth, monthly average snowfall, and monthly average wind speed.

5. The avalanche disaster risk method according to claim 4, wherein The avalanche dynamic assessment model is expressed as: ； ； ； ； ； ； Wherein, are the avalanche susceptibility index values for January, February, March, April, May, and December, respectively; , , , , , , , , , , are the normalized elevation, slope, curvature, topographic relief, distance to river, coefficient of variation of factor elevation, NDVI, average monthly snowfall in the nth month, average monthly snow depth in the nth month, average monthly snow cover in the nth month, and average monthly wind speed in the nth month, where n = 1, 2, 3, 4, 5, 12.

6. The avalanche disaster risk method according to claim 5, characterized in that Based on the avalanche dynamic assessment model, assessing the avalanche disaster risk of the target area: Obtaining the real-time disaster-forming background data of the target area, and determining the avalanche disaster-forming factors based on the real-time disaster-forming background data; Normalizing the avalanche disaster-forming factors to obtain normalized avalanche disaster-forming factors; Substituting the normalized avalanche disaster-forming factors into the avalanche dynamic assessment model to obtain the avalanche susceptibility index value; Based on the avalanche susceptibility index value, an avalanche susceptibility index distribution map of the target area is established to evaluate the avalanche disaster risk of the target area.

7. The avalanche disaster risk method according to claim 6, characterized in that, The avalanche disaster-causing factors are normalized by the following formula to obtain the normalized avalanche disaster-causing factors: ； where Dem represents elevation, and Dem max is the maximum elevation; Slope represents slope, and Slope max is the maximum slope; Cur represents curvature, and Cur max is the maximum curvature; Ula represents the terrain undulation degree, Ula max is the maximum value of the terrain undulation degree; Var represents the coefficient of variation of elevation, Var max is the maximum value of the coefficient of variation of elevation; D represents the distance from the river, D max is the maximum value of the distance from the river; NDVI represents the normalized difference vegetation index, NDVI max is the maximum value of the normalized difference vegetation index; Sf represents the snowfall, Sf max is the maximum value of the snowfall; Sdp represents the snow depth, Sdp max is the maximum value of the snow depth; Cov represents snow cover, Cov max is the maximum snow cover; Wind represents wind speed, Wind max is the maximum wind speed.

8. An avalanche disaster risk system, characterized in that, The system includes: A data preprocessing module, configured to obtain avalanche occurrence data and disaster-causing background data of the target area, and determine avalanche disaster-causing factors according to the disaster-causing background data; A model training module, configured to, based on the avalanche occurrence data of the target area, use avalanche points as positive samples, collect non-avalanche points as negative samples in a ratio of 1:1 with the positive samples to construct training data, construct a random forest model, and use the training data to train the random forest model. During training, the avalanche points are used as the labels of the training samples, and the avalanche disaster-causing factors are used as the input features of the random forest model. The factor weights are determined according to the splitting contribution degree of the input features on the decision tree of the random forest model to obtain an avalanche dynamic assessment model; A risk assessment module, configured to evaluate the avalanche disaster risk of the target area based on the avalanche dynamic assessment model.

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

10. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by the processor, they are used to implement the avalanche disaster risk method according to any one of claims 1-7.

Images