Monte Carlo-based automatic generation method and system for potential landslide sliding range

Abstract

The present invention discloses a Monte Carlo-based method and system for automatically generating the potential landslide slip range. The method comprises: S1, determining a potential initial slip point grid; S2, constructing a Monte Carlo slope random slip algorithm based on the potential initial slip point grid; S3, performing a Monte Carlo slope slip simulation; and S4, counting the frequency of each grid in the slip path being selected by the slip simulation, converting the grid frequency statistics into a potential landslide slip probability value, and classifying the values ​​to generate the potential landslide slip range. The Monte Carlo-based method for automatically generating the potential landslide slip range proposed in the present invention cleverly utilizes the mountain movement precursor information detected by InSAR technology to accurately locate potential landslide hazards. By drawing on the Monte Carlo random walk concept to simulate the longitudinal and lateral movement of potential landslides, it achieves automatic prediction of large-scale potential landslide slip ranges.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic prediction of potential landslide sliding range, and in particular to a method and system for automatically generating potential landslide sliding range based on Monte Carlo. Background Art

[0002] Once a landslide occurs, its impact is widespread. The resulting collapse, debris flow, and other sliding movements pose a serious threat to people, houses, roads, and other infrastructure located along the landslide path. Landslides typically occur in the sliding zone along the slope rather than at the initial stage. Therefore, rapid and automated prediction of the potential landslide range before a disaster occurs is crucial for landslide monitoring, early warning, and disaster prevention and mitigation efforts.

[0003] With the deepening of research into landslide movement mechanisms and the rapid development of computer data processing capabilities, significant progress has been made in simulating the potential slip range of landslides. Current methods for simulating landslide slip range are mainly divided into empirical and modeling approaches. The empirical approach uses the maximum slip distance and accessible angle as slip calculation indicators, and predicts the slip range by fitting empirical equations with relevant statistical data from historical landslide data. The modeling approach uses geophysical models to simulate the landslide movement process and predict the slip range of individual landslides. However, there are still many problems to be overcome in the current automatic simulation technology of landslide sliding range: First, the prediction accuracy of the empirical method is low, and it relies on existing statistical data. There is a lack of historical statistical data on large-scale landslides, making it difficult to effectively apply to engineering scenarios; Second, the modeling method needs to take into account the complex local geological conditions, and the calculation process relies on complete geotechnical parameters. However, in actual engineering tasks, there is a lack of reliable relevant parameters, and it is impossible to quickly generate the landslide sliding range in large-scale areas; Third, current methods all assume that landslides have already occurred, and the prediction results are more of a reconstruction of the sliding process of historical landslide points rather than a simulation of the potential sliding range of the mountain. Landslides are highly sudden and difficult to prevent. It is difficult to achieve good results by directly applying these methods to the potential landslide disaster monitoring and early warning business. Summary of the Invention

[0004] In view of the shortcomings of the prior art, the present invention provides a method for automatically generating the potential landslide sliding range based on Monte Carlo, the method comprising:

[0005] S1. Based on multi-temporal radar image data, radar interferometry technology and deep learning models are used to identify landslide hazards, build a landslide hazard database, and use a differentiated sampling strategy that takes into account the hazard scale to determine the potential initial slip point grid from the landslide hazards;

[0006] S2. Based on the potential initial slip point grid, construct a Monte Carlo slope random slip algorithm, including: designing walking parameters that take into account the terrain and movement direction, simulating the longitudinal and lateral movement of the landslide, and constructing a formula to calculate the random probability of the current slip grid sliding to the target grid;

[0007] S3. Performing a Monte Carlo slope slide simulation based on the Monte Carlo random slide algorithm, including: constructing a farthest slide constraint rule that takes into account the sliding height difference and area as a slide cutoff condition, optimizing the slide cutoff condition based on historical landslide data, determining the sliding terrain based on the terrain relief factor, and designing a Monte Carlo flatland random walk rule when a potential sliding point enters the bottom of the slope, and continuing to simulate the landslide movement process until the slide cutoff condition is reached or the target grid no longer exists;

[0008] S4. Based on the historical landslide statistics of the current area, the walking parameters that take into account the terrain and movement direction are adjusted, the frequency of each grid in the slip path being selected by the slip simulation is counted, the grid frequency statistics are converted into potential landslide probability values ​​and classified, and the potential landslide slip range is generated.

[0009] Preferably, step S1 includes:

[0010] The radar interferometry technology and deep learning model are used to identify landslide hazards using multi-temporal radar image data. The calculation formula is:

[0011] L=E(F(D1))+E(F(D2)) (1)

[0012] Wherein, D1 and D2 represent the radar satellite ascending and descending orbit data in the multi-temporal radar image data, respectively; F represents the calculation of the surface deformation rate using the ascending and descending orbit data using radar interferometry technology; E represents the automatic identification of landslide hazards based on the surface deformation rate using a deep learning model; and L represents the landslide hazard identification result by integrating the ascending and descending orbit data.

[0013] Constructing a landslide hazard database, and performing vectorization, data statistics, and geometric screening and normalization processing on the landslide hazard identification results;

[0014] A differentiated sampling strategy that takes into account the scale of the hazard is used to determine the potential initial slip point grid from the landslide hazard. The calculation formula is:

[0015]

[0016] x i (m) = x i (mpR) (3)

[0017] Where X represents the potential initial slip point grid, x irepresents the i-th hidden danger grid, n represents the number of identified hidden dangers, m represents a single hidden danger grid data sequence, R represents the resolution of the DEM grid data, p represents the sampling interval, and i and n are positive integers.

[0018] Preferably, step S2 includes:

[0019] Design the walking parameter L that takes into account the direction of movement during the Monte Carlo random walk ctrl This parameter is used to define the backward search distance. The direction control grid of the current sliding grid is located according to the backward search distance. The distance between the sliding grid and the direction control grid must be greater than the walk parameter L for the next sliding grid. ctrl , through the walk parameter L ctrl Constrain the direction of random walk of potential sliding points in the DEM grid;

[0020] Designing the terrain-sensitive walk parameter R during Monte Carlo random walks max This parameter is used to define the highest elevation in the sliding simulation process. The elevation difference between each sliding grid and the previous sliding grid in the sliding simulation process cannot be greater than the walking parameter R max , walk parameter R max Usually it is 1 / 5 of the resolution of the DEM raster data, and the walking parameter R max Unreasonable upward motion during constrained slip simulation.

[0021] Preferably, in step S2, a random probability calculation formula for the current sliding grid sliding to the target grid is constructed, and the calculation formula is:

[0022]

[0023] Among them, P px is the probability that the target grid around the current sliding grid becomes the next sliding grid, n is the number of target grids, β is the slope between the current sliding grid and the target grid, f d and f β They are weight factors for adjusting the sliding direction and slope respectively. When the direction of the next sliding grid is the same as the previous one, f d d 2 , when the sliding direction changes by 45°, f d is d, when the sliding direction changes 90°, f d is 1, f β and d are initialization input parameters.

[0024] Preferably, step S3 includes:

[0025] A terrain undulation factor is designed to determine the slip terrain. If the terrain undulation factor is less than the slope threshold, a Monte Carlo flat-land random walk rule is constructed based on the random probability calculation formula, and the control of the walk parameters taking the terrain into consideration is released, thereby realizing the transition of the Monte Carlo slip simulation from slope to flat terrain.

[0026] Preferably, in step S3, a maximum slip constraint rule taking into account the slip height difference and area is constructed as a slip cutoff condition, and the slip cutoff condition is optimized according to historical landslide data, including:

[0027] A slip distance cutoff formula that takes into account the slip height difference and the hidden danger area is constructed. Assuming that the maximum slip distance is a continuous smooth function of the slip height difference and the hidden danger area, that is, the slip cutoff condition F, Taylor expansion of this function at zero point can obtain the multivariate regression formula of the maximum slip distance:

[0028]

[0029] Among them, x1 is the slip height difference, x2 is the hidden danger area, Q n is x n The influence coefficient, Q m is the cross-influence coefficient of sliding height difference and hidden danger area on sliding distance;

[0030] According to the historical landslide data, the fitting formula of the slip cutoff condition F is obtained through multiple regression:

[0031] F(x1,x2)=3.089x1 0.47 +4.258x2 0.43 -173.476 (9)

[0032] Design distance segmentation parameter L seg Calculate the longest sliding distance during the sliding process and divide the parameter L by distance seg The sliding path is divided into sub-paths. The maximum sliding distance is the sum of the sub-paths. The calculation formula is:

[0033]

[0034] Among them, L is the current farthest sliding distance, and n is the number of divided sub-paths.

[0035] Set the maximum number of random walks n max , and perform n simultaneous operations on potential initial slip points max If the current maximum sliding distance L exceeds the sliding cutoff condition F or the target grid does not exist, the sliding is ended and the number of times each grid is selected by random sliding is stored.

[0036] Preferably, step S4 includes:

[0037] Geographical spatial analysis techniques are used to count the frequency of each grid in the slip path being selected for slip simulation. The walking parameters that take into account the terrain and movement direction are adjusted according to the historical landslide statistics of the current area. This process is iterated continuously until the optimal effect is achieved. The optimal simulation results are output as GIS visualization, and the grid frequency statistics are converted into potential landslide slip probability values. The natural breakpoint method is used to classify the potential landslide slip probability values ​​to generate the potential landslide slip range.

[0038] Preferably, step S4 includes:

[0039] S41. For the slippage influence grids triggered by the same hidden danger and all hidden danger slippage points, different methods are used to count the selection frequencies. The calculation formula is:

[0040] S=max(s i ),i∈n (11)

[0041]

[0042] Among them, S represents the selection frequency of the same hidden danger, s i Indicates the selection frequency of the i-th slip point within the hidden danger, S sum represents the selection frequency of all potential danger slip points, m represents the number of potential dangers affecting the target grid, i, j, n, m are positive integers;

[0043] S42. Convert grid frequency statistics into slip impact probability values. The calculation formula is:

[0044]

[0045] Among them, P represents the slip impact probability value, S sum Indicates the selection frequency of all potential slip points, n max represents the maximum number of random walks;

[0046] S43. Use the natural breakpoint classification method to divide the slip impact probability value into three impact range levels: high, medium and low, and generate the potential landslide slip range.

[0047] Based on the same inventive concept, the present invention also provides a system for automatically generating the potential landslide sliding range based on Monte Carlo theory, the system comprising:

[0048] An initial slip point determination module is used to identify landslide hazards based on multi-temporal radar image data using radar interferometry technology and deep learning models, build a landslide hazard database, and determine the potential initial slip point grid from the landslide hazards using a differentiated sampling strategy that takes into account the hazard scale;

[0049] A sliding algorithm construction module is used to construct a Monte Carlo slope random sliding algorithm based on the potential initial sliding point grid, including: designing walking parameters that take into account the terrain and movement direction, simulating the longitudinal and lateral movement process of the landslide, and constructing a random probability calculation formula for the current sliding grid sliding to the target grid;

[0050] A slope sliding simulation module is used to perform Monte Carlo slope sliding simulation based on the Monte Carlo random sliding algorithm, including: constructing a farthest sliding constraint rule that takes into account the sliding height difference and area as a sliding cutoff condition, optimizing the sliding cutoff condition based on historical landslide data, judging the sliding terrain based on the terrain relief factor, and designing a Monte Carlo flat ground random walk rule when a potential sliding point enters the bottom of the slope to continue simulating the landslide movement process until the sliding cutoff condition is reached or the target grid does not exist;

[0051] The sliding range generation module is used to adjust the walking parameters that take into account the terrain and movement direction based on the historical landslide statistics of the current area, count the frequency of each grid in the sliding path being selected by the sliding simulation, convert the grid frequency statistics into potential landslide slip probability values ​​and classify them to generate the potential landslide slip range.

[0052] Preferably, the initial slip point determination module is specifically used to:

[0053] The radar interferometry technology and deep learning model are used to identify landslide hazards using multi-temporal radar image data. The calculation formula is:

[0054] L=E(F(D1))+E(F(D2)) (1)

[0055] Wherein, D1 and D2 represent the radar satellite ascending and descending orbit data in the multi-temporal radar image data, respectively; F represents the calculation of the surface deformation rate using the ascending and descending orbit data using radar interferometry technology; E represents the automatic identification of landslide hazards based on the surface deformation rate using a deep learning model; and L represents the landslide hazard identification result by integrating the ascending and descending orbit data.

[0056] Constructing a landslide hazard database, and performing vectorization, data statistics, and geometric screening and normalization processing on the landslide hazard identification results;

[0057] A differentiated sampling strategy that takes into account the scale of the hazard is used to determine the potential initial slip point grid from the landslide hazard. The calculation formula is:

[0058]

[0059] x i (m) = x i (mpR) (3)

[0060] Where X represents the potential initial slip point grid, x i represents the i-th hidden danger grid, n represents the number of identified hidden dangers, m represents a single hidden danger grid data sequence, R represents the resolution of the DEM grid data, p represents the sampling interval, and i and n are positive integers.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] The present invention first uses InSAR technology to detect surface micro-deformations, identify deformation clusters in mountainous areas, construct a landslide hazard dataset, and determine potential landslide slip points. Based on the Monte Carlo method, the mountain slip process and maximum slip distance constraint rules are then formulated. Multiple random walk simulations are performed on the slip points in a GIS environment to generate potential slip range prediction results. The present invention utilizes the mountain movement precursor information detected by InSAR technology to accurately locate potential landslide hazards. By drawing on the Monte Carlo random walk method, the longitudinal and lateral movements of potential landslides are simulated, achieving automatic prediction of large-scale potential landslide slip ranges. This improves the problems of traditional landslide slip prediction methods, such as the need for complex model parameters and poor applicability to large-scale slip prediction tasks. It can be quickly and effectively applied to engineering services such as landslide hazard risk assessment, and is of great significance for improving the intelligent level of landslide disaster monitoring and early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A flow chart of a method for automatically generating a potential landslide sliding range based on Monte Carlo provided by the present invention;

[0064] Figure 2 A technical flow chart of a Monte Carlo-based method for automatically generating the potential landslide sliding range provided by the present invention;

[0065] Figure 3 Schematic diagram of the potential slip simulation process based on Monte Carlo random walk provided by the present invention;

[0066] Figure 4 A schematic diagram of the sliding direction constraint based on Monte Carlo random walk provided by the present invention;

[0067] Figure 5 A schematic diagram of the sliding distance calculation method based on Monte Carlo random walk provided by the present invention;

[0068] Figure 6 This is a schematic diagram of the simulation results of the potential landslide sliding range in Zhouqu County provided by the present invention. DETAILED DESCRIPTION

[0069] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0070] The present invention will be described in further detail below with reference to the accompanying drawings.

[0071] like Figure 1-2 As shown, an embodiment of the present invention provides a method for automatically generating a potential landslide sliding range based on Monte Carlo, comprising:

[0072] S1. Based on multi-temporal radar image data, radar interferometry technology and deep learning models are used to identify landslide hazards, build a landslide hazard database, and use a differentiated sampling strategy that takes into account the hazard scale to determine the potential initial slip point grid from the landslide hazards;

[0073] S2. Based on the potential initial slip point grid, a Monte Carlo random slope sliding algorithm is constructed, including: designing walking parameters that take into account the terrain and movement direction, simulating the longitudinal and lateral movement of the landslide, and constructing a formula to calculate the random probability of the current sliding grid sliding to the target grid;

[0074] S3. Monte Carlo slope slip simulation based on the Monte Carlo random slip algorithm, including: constructing a maximum slip constraint rule that takes into account the slip height difference and area as the slip cutoff condition, optimizing the slip cutoff condition based on historical landslide data, determining the slip topography based on the terrain relief factor, and designing a Monte Carlo flat random walk rule when a potential slip point reaches the bottom of the slope to continue simulating the landslide movement process until the slip cutoff condition is reached or the target grid no longer exists;

[0075] S4. Based on the historical landslide statistics of the current area, the walking parameters that take into account the terrain and movement direction are adjusted. The frequency of each grid in the slip path being selected by the slip simulation is counted. The grid frequency statistics are converted into potential landslide probability values ​​and classified to generate the potential landslide slip range.

[0076] like Figure 3As shown, for step S1, the surface deformation rate is calculated based on multi-temporal radar images using radar interferometry technology (InSAR), landslide hazards are identified through deep learning artificial intelligence models, and the hazard database is normalized by vectorization, data statistics, geometric screening, etc. to construct a landslide hazard database. A differentiated sampling strategy that takes into account the hazard scale is used to determine the potential landslide starting point from the landslide hazard, and the migration of surface micro-motion information detected by InSAR to potential slip points is realized, providing high-quality slip starting point data for potential landslide slip range simulation.

[0077] Step S1 includes:

[0078] S11. Use radar interferometry technology and deep learning models to identify landslide hazards using multi-temporal radar image data. The calculation formula is:

[0079] L=E(F(D1))+E(F(D2)) (1)

[0080] Among them, D1 and D2 represent the ascending and descending radar satellite data in the multi-temporal radar image data, respectively. F represents the calculation of surface deformation rate using the ascending and descending data using radar interferometry technology. E represents the automatic identification of landslide hazards based on the surface deformation rate using a deep learning model. L represents the landslide hazard identification result by integrating the ascending and descending data.

[0081] S12, constructing a landslide hazard database, and performing vectorization, data statistics, and geometric screening and normalization processing on the landslide hazard identification results;

[0082] S13. A differentiated sampling strategy that takes into account the scale of the hazard is used to determine the potential initial slip point grid from the landslide hazard. The calculation formula is:

[0083]

[0084] x i (m) = x i (mpR) (3)

[0085] Where X represents the potential initial slip point grid, x i represents the i-th hidden danger grid, n represents the number of identified hidden dangers, m represents a single hidden danger grid data sequence, R represents the resolution of the DEM grid data, p represents the sampling interval, and i and n are positive integers.

[0086] For step S2, a slope Monte Carlo landslide random walk algorithm is constructed. The longitudinal and lateral movement processes of the slip are simulated by designing walk parameters and rules that take into account the terrain and movement direction. The random slip probability calculation formula is used to realize the random walk of the slip point between the DEM grid data. The walk parameters are initialized according to the DEM data resolution and hidden danger scale information.

[0087] Step S2 includes:

[0088] S21. The direction of slip motion usually does not change drastically, e.g. Figure 4 As shown, the walking parameter L that takes into account the direction of movement in the design of Monte Carlo random walk process ctrl This parameter is used to define the backward search distance. The direction control grid of the current sliding grid is located according to the backward search distance. The distance between the next sliding grid and the direction control grid must be greater than the walk parameter L ctrl , through the walk parameter L ctrl Constrain the direction of random walk of potential sliding points in the DEM grid;

[0089] S22. Design the terrain-sensitive walk parameter R during the Monte Carlo random walk process max This parameter is used to define the highest elevation in the sliding simulation process. The elevation difference between each sliding grid and the previous sliding grid in the sliding simulation process cannot be greater than the walking parameter R max , walk parameter R max Usually it is 1 / 5 of the resolution of the DEM raster data, and the walking parameter R max Unreasonable upward motion during constraint slip simulation;

[0090] S23, construct a random probability calculation formula for the current sliding grid sliding to the target grid, the calculation formula is:

[0091]

[0092] Among them, P px is the probability that the target grid around the current sliding grid becomes the next sliding grid, n is the number of target grids, β is the slope between the current sliding grid and the target grid, f d and f β They are weight factors for adjusting the sliding direction and slope respectively. When the direction of the next sliding grid is the same as the previous one, f d d 2 , when the sliding direction changes by 45°, f d is d, when the sliding direction changes 90°, f d is 1, f β and d are initialization input parameters.

[0093] In an embodiment of the present invention, for step S3, a maximum slip constraint rule that takes into account the slip height difference and area is designed as a slip cutoff condition. The cutoff condition can be continuously optimized through historical landslide data. A large number of random walks are performed on the slip starting point simultaneously according to the Monte Carlo walk algorithm constructed in step 2. The slip position is determined based on the terrain factors. When the slip point enters the bottom of the slope, a flat ground random walk rule is designed to continue simulating the landslide movement process until the slip cutoff condition is reached or the target slip grid no longer exists during the walk.

[0094] Step S3 includes:

[0095] S31. Design a terrain relief factor to determine the slip terrain. If the terrain relief factor is less than the slope threshold, construct a Monte Carlo flat-land random walk rule based on a random probability calculation formula, remove the control of the walk parameters that take the terrain into account, and realize the transition of the Monte Carlo slip simulation from slope to flat terrain.

[0096] S32. Construct a slip distance cutoff formula that takes into account the slip height difference and the potential hazard area. Assume that the maximum slip distance is a continuous smooth function of the slip height difference and the potential hazard area, i.e., the slip cutoff condition F. Perform Taylor expansion of this function at zero to obtain the multivariate regression formula for the maximum slip distance:

[0097]

[0098] Among them, x1 is the slip height difference, x2 is the hidden danger area, Q n is x n The influence coefficient, Q m is the cross-influence coefficient of sliding height difference and hidden danger area on sliding distance;

[0099] According to the historical landslide data, the fitting formula of the slip cutoff condition F is obtained through multiple regression:

[0100] F(x1,x2)=3.089x1 0.47 +4.258x2 0.43 -173.476 (9)

[0101] S33, because the random walk process will produce uneven sliding grids, directly using the sum of the sliding grid distances will cause a large deviation between the calculated results and the actual distance in the main sliding direction. seg Calculate the longest sliding distance during the sliding process and divide the parameter L by distance seg The sliding path is divided into sub-paths, and the maximum sliding distance is the sum of the sub-paths, such as Figure 5 As shown, the calculation formula is:

[0102]

[0103] Among them, L is the current farthest sliding distance, and n is the number of divided sub-paths.

[0104] S34. Set the maximum number of random walks n max , and perform n simultaneous operations on potential initial slip points max If the current maximum sliding distance L exceeds the sliding cutoff condition F or the target grid does not exist, the sliding is ended and the number of times each grid is selected by random sliding is stored.

[0105] In the embodiment of the present invention, step S4 includes:

[0106] The frequency of selected slip simulations for each grid in the slip path is statistically analyzed using geospatial analysis techniques. The walking parameters that take into account the terrain and movement direction are adjusted based on historical landslide statistics in the current area. This process is iterated continuously until the optimal effect is achieved. The optimal simulation results are visualized in GIS, and the grid frequency statistics are converted into potential landslide slip probability values. The natural breakpoint method is used to classify the potential landslide slip probability values ​​to generate the potential landslide slip range.

[0107] Step S4 includes:

[0108] S41. For the slippage influence grids triggered by the same hidden danger and all hidden danger slippage points, different methods are used to count the selection frequencies. The calculation formula is:

[0109] S=max(s i ),i∈n (11)

[0110]

[0111] Among them, S represents the selection frequency of the same hidden danger, s i Indicates the selection frequency of the i-th slip point within the hidden danger, S sum represents the selection frequency of all potential danger slip points, m represents the number of potential dangers affecting the target grid, i, j, n, m are positive integers;

[0112] S42. Convert grid frequency statistics into slip impact probability values. The calculation formula is:

[0113]

[0114] Among them, P represents the slip impact probability value, S sum Indicates the selection frequency of all potential slip points, n max represents the maximum number of random walks;

[0115] S43. The natural breakpoint classification method is used to divide the slip impact probability value into three impact range levels: high, medium and low.

[0116] like Figure 6 Figure 1 shows the simulation results of the potential landslide range in Zhouqu County. The boxes ①, ②, and ③ in the left figure represent three landslide hazards identified by InSAR. The top three figures correspond to the impact probabilities of the three landslide hazards, while the bottom three figures correspond to the impact levels of the three landslide hazards. This provides an intuitive understanding of the potential landslide range.

[0117] The embodiment of the present invention further provides a system for automatically generating the potential landslide sliding range based on Monte Carlo theory, comprising:

[0118] The initial slip point determination module is used to identify landslide hazards based on multi-temporal radar image data using radar interferometry technology and deep learning models, build a landslide hazard database, and determine the potential initial slip point grid from landslide hazards using a differentiated sampling strategy that takes into account the hazard scale;

[0119] The sliding algorithm construction module is used to construct a Monte Carlo random slope sliding algorithm based on a grid of potential initial sliding points. This includes: designing walking parameters that take into account the terrain and movement direction, simulating the longitudinal and lateral movement of the landslide, and constructing a formula to calculate the random probability of the current sliding grid sliding to the target grid;

[0120] The slope sliding simulation module is used to perform Monte Carlo slope sliding simulation based on the Monte Carlo random sliding algorithm. This includes: constructing a maximum sliding constraint rule that takes into account the sliding height difference and area as the sliding cutoff condition, optimizing the sliding cutoff condition based on historical landslide data, determining the sliding terrain based on the terrain relief factor, and designing a Monte Carlo flat random walk rule when a potential sliding point reaches the bottom of the slope to continue simulating the landslide movement process until the sliding cutoff condition is reached or the target grid no longer exists;

[0121] The slip range generation module is used to adjust the walking parameters that take into account the terrain and movement direction based on the historical landslide statistics of the current area, count the frequency of each grid in the slip path being selected by the slip simulation, convert the grid frequency statistics into potential landslide slip probability values ​​and classify them to generate the potential landslide slip range.

[0122] The present invention integrates InSAR detection of landslide hazards into the potential landslide slip simulation algorithm by designing a slip starting point sampling strategy that takes into account the scale of the hazard, achieving the adaptation of InSAR surface deformation information and the driving force of the potential landslide, and effectively solving the problem that traditional InSAR technology can only detect the slip starting area of ​​the potential landslide but cannot assess the slip impact range; by constructing a random slip algorithm based on the Monte Carlo concept, the longitudinal and lateral slip movement process of the potential landslide is effectively simulated. Combined with the slip constraint conditions that take into account the slip area and height difference, the problem that the traditional landslide impact range simulation method is difficult to expand to large-scale applications is solved, and the rapid and automatic prediction of the potential landslide slip impact range is achieved.

[0123] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A Monte Carlo-based method for automatically generating the potential landslide sliding range, characterized in that: The method comprises: S1. Based on multi-temporal radar image data, radar interferometry technology and deep learning models are used to identify landslide hazards, build a landslide hazard database, and use a differentiated sampling strategy that takes into account the hazard scale to determine the potential initial slip point grid from the landslide hazards; S2. Based on the potential initial slip point grid, construct a Monte Carlo slope random slip algorithm, including: designing walking parameters that take into account the terrain and movement direction, simulating the longitudinal and lateral movement of the landslide, and constructing a formula to calculate the random probability of the current slip grid sliding to the target grid; S3. Performing a Monte Carlo slope slide simulation based on the Monte Carlo random slide algorithm, including: constructing a farthest slide constraint rule that takes into account the sliding height difference and area as a slide cutoff condition, optimizing the slide cutoff condition based on historical landslide data, determining the sliding terrain based on the terrain relief factor, and designing a Monte Carlo flatland random walk rule when a potential sliding point enters the bottom of the slope, and continuing to simulate the landslide movement process until the slide cutoff condition is reached or the target grid no longer exists; S4. Based on the historical landslide statistics of the current area, the walking parameters that take into account the terrain and movement direction are adjusted, the frequency of each grid in the slip path being selected by the slip simulation is counted, the grid frequency statistics are converted into potential landslide probability values ​​and classified, and the potential landslide slip range is generated.

2. The method according to claim 1, characterized in that Step S1 includes: The radar interferometry technology and deep learning model are used to identify landslide hazards using multi-temporal radar image data. The calculation formula is: L=E(F(D1))+E(F(D2)) (1) Wherein, D1 and D2 represent the radar satellite ascending and descending orbit data in the multi-temporal radar image data, respectively; F represents the calculation of the surface deformation rate using the ascending and descending orbit data using radar interferometry technology; E represents the automatic identification of landslide hazards based on the surface deformation rate using a deep learning model; and L represents the landslide hazard identification result by integrating the ascending and descending orbit data. Constructing a landslide hazard database, and performing vectorization, data statistics, and geometric screening and normalization processing on the landslide hazard identification results; A differentiated sampling strategy that takes into account the scale of the hazard is used to determine the potential initial slip point grid from the landslide hazard. The calculation formula is: x i (m)=x i (mpR) (3) Where X represents the potential initial slip point grid, x i represents the i-th hidden danger grid, n represents the number of identified hidden dangers, m represents a single hidden danger grid data sequence, R represents the resolution of the DEM grid data, p represents the sampling interval, and i and n are positive integers.

3. The method according to claim 2, characterized in that Step S2 includes: Design the walking parameter L that takes into account the direction of movement during the Monte Carlo random walk ctrl This parameter is used to define the backward search distance. The direction control grid of the current sliding grid is located according to the backward search distance. The distance between the sliding grid and the direction control grid must be greater than the walk parameter L for the next sliding grid. ctrl , through the walk parameter L ctrl Constrain the direction of random walk of potential sliding points in the DEM grid; Designing the terrain-sensitive walk parameter R during Monte Carlo random walks max This parameter is used to define the highest elevation in the sliding simulation process. The elevation difference between each sliding grid and the previous sliding grid in the sliding simulation process cannot be greater than the walking parameter R max , walk parameter R max Usually it is 1 / 5 of the resolution of the DEM raster data, and the walking parameter R max Unreasonable upward motion during constrained slip simulation.

4. The method according to claim 1, wherein In step S2, a random probability calculation formula for the current sliding grid sliding to the target grid is constructed, and the calculation formula is: Among them, P px is the probability that the target grid around the current sliding grid becomes the next sliding grid, n is the number of target grids, β is the slope between the current sliding grid and the target grid, f d and f β They are weight factors for adjusting the sliding direction and slope respectively. When the direction of the next sliding grid is the same as the previous one, f d d 2 , when the sliding direction changes by 45°, f d is d, when the sliding direction changes 90°, f d is 1, f β and d are initialization input parameters.

5. The method according to claim 1, wherein Step S3 includes: A terrain undulation factor is designed to determine the slip terrain. If the terrain undulation factor is less than the slope threshold, a Monte Carlo flat-land random walk rule is constructed based on the random probability calculation formula, and the control of the walk parameters taking the terrain into consideration is released, thereby realizing the transition of the Monte Carlo slip simulation from slope to flat terrain.

6. The method according to claim 1, characterized in that In step S3, a maximum slip constraint rule taking into account the slip height difference and area is constructed as a slip cutoff condition, and the slip cutoff condition is optimized based on historical landslide data, including: A slip distance cutoff formula that takes into account the slip height difference and the hidden danger area is constructed. Assuming that the maximum slip distance is a continuous smooth function of the slip height difference and the hidden danger area, that is, the slip cutoff condition F, Taylor expansion of this function at zero point can obtain the multivariate regression formula of the maximum slip distance: Among them, x1 is the slip height difference, x2 is the hidden danger area, Q n is x n The influence coefficient, Q m is the cross-influence coefficient of sliding height difference and hidden danger area on sliding distance; According to the historical landslide data, the fitting formula of the slip cutoff condition F is obtained through multiple regression: <h2 style=";text-align:left;direction:ltr">F(x1,x2)=3.089x1<h2 style=";text-align:left;direction:ltr"> 0.47 <h2 style=";text-align:left;direction:ltr"> +4.258x2<h2 style=";text-align:left;direction:ltr"> 0.43 <h2 style=";text-align:left;direction:ltr"> -173.476 (9) Design distance segmentation parameter L seg Calculate the longest sliding distance during the sliding process and divide the parameter L by distance seg The sliding path is divided into sub-paths. The maximum sliding distance is the sum of the sub-paths. The calculation formula is: Among them, L is the current farthest sliding distance, and n is the number of divided sub-paths; Set the maximum number of random walks n max , and perform n simultaneous operations on potential initial slip points max If the current maximum sliding distance L exceeds the sliding cutoff condition F or the target grid does not exist, the sliding is ended and the number of times each grid is selected by random sliding is stored.

7. The method according to claim 1, characterized in that Step S4 includes: Geographical spatial analysis techniques are used to count the frequency of each grid in the slip path being selected for slip simulation. The walking parameters that take into account the terrain and movement direction are adjusted according to the historical landslide statistics of the current area. This process is iterated continuously until the optimal effect is achieved. The optimal simulation results are output as GIS visualization, and the grid frequency statistics are converted into potential landslide slip probability values. The natural breakpoint method is used to classify the potential landslide slip probability values ​​to generate the potential landslide slip range.

8. The method according to claim 1, characterized in that Step S4 includes: S41. For the slippage influence grids triggered by the same hidden danger and all hidden danger slippage points, different methods are used to count the selection frequencies. The calculation formula is: S=max(s i ),i∈n (11) Among them, S represents the selection frequency of the same hidden danger, s i Indicates the selection frequency of the i-th slip point within the hidden danger, S sum represents the selection frequency of all potential danger slip points, m represents the number of potential dangers affecting the target grid, n represents the number of sampled slip points in a single potential danger, i, j, n are positive integers; S42. Convert grid frequency statistics into slip impact probability values. The calculation formula is: Among them, P represents the slip impact probability value, S sum Indicates the selection frequency of all potential slip points, n max represents the maximum number of random walks; S43. Use the natural breakpoint classification method to divide the slip impact probability value into three impact range levels: high, medium and low, and generate the potential landslide slip range.

9. A system for automatically generating potential landslide sliding range based on Monte Carlo theory, used to implement the method according to any one of claims 1 to 8, characterized in that: The system comprises: An initial slip point determination module is used to identify landslide hazards based on multi-temporal radar image data using radar interferometry technology and deep learning models, build a landslide hazard database, and determine the potential initial slip point grid from the landslide hazards using a differentiated sampling strategy that takes into account the hazard scale; A sliding algorithm construction module is used to construct a Monte Carlo slope random sliding algorithm based on the potential initial sliding point grid, including: designing walking parameters that take into account the terrain and movement direction, simulating the longitudinal and lateral movement process of the landslide, and constructing a random probability calculation formula for the current sliding grid sliding to the target grid; A slope sliding simulation module is used to perform Monte Carlo slope sliding simulation based on the Monte Carlo random sliding algorithm, including: constructing a farthest sliding constraint rule that takes into account the sliding height difference and area as a sliding cutoff condition, optimizing the sliding cutoff condition based on historical landslide data, judging the sliding terrain based on the terrain relief factor, and designing a Monte Carlo flat ground random walk rule when a potential sliding point enters the bottom of the slope to continue simulating the landslide movement process until the sliding cutoff condition is reached or the target grid does not exist; The sliding range generation module is used to adjust the walking parameters that take into account the terrain and movement direction based on the historical landslide statistics of the current area, count the frequency of each grid in the sliding path being selected by the sliding simulation, convert the grid frequency statistics into potential landslide slip probability values ​​and classify them to generate the potential landslide slip range.

10. The system according to claim 9, characterized in that The initial slip point determination module is specifically used for: The radar interferometry technology and deep learning model are used to identify landslide hazards using multi-temporal radar image data. The calculation formula is: L=E(F(D1))+E(F(D2)) (1) Wherein, D1 and D2 represent the radar satellite ascending and descending orbit data in the multi-temporal radar image data, respectively; F represents the calculation of the surface deformation rate using the ascending and descending orbit data using radar interferometry technology; E represents the automatic identification of landslide hazards based on the surface deformation rate using a deep learning model; and L represents the landslide hazard identification result by integrating the ascending and descending orbit data. Constructing a landslide hazard database, and performing vectorization, data statistics, and geometric screening and normalization processing on the landslide hazard identification results; A differentiated sampling strategy that takes into account the scale of the hazard is used to determine the potential initial slip point grid from the landslide hazard. The calculation formula is: x i (m)=x i (mpR) (3) Where X represents the potential initial slip point grid, x i represents the i-th hidden danger grid, n represents the number of identified hidden dangers, m represents a single hidden danger grid data sequence, R represents the resolution of the DEM grid data, p represents the sampling interval, and i and n are positive integers.

Images