Landslide Susceptibility Assessment Method and Device Considering the Influence Factor Action Intensity

Abstract

The present invention discloses a landslide susceptibility assessment method and device considering the action intensity of influence factors. The method includes: determining a plurality of slope units from the area to be evaluated based on digital elevation model data; performing interval division processing on a plurality of landslide influence factors within the area to be evaluated; quantifying the action intensity of each landslide influence factor after the interval division processing on the occurrence of landslides; determining the landslide influence factors considering the action intensity included in each slope unit according to the coordinate range of each slope unit, and taking the landslide influence factor with the maximum action intensity in each slope unit as the factor of the action intensity of the landslide influence factor in each current considered slope unit; inputting the factors of the action intensity of the landslide influence factor in a plurality of current considered slope units into a landslide susceptibility assessment model to obtain a landslide susceptibility assessment result. The present invention can consider the action intensity of the landslide influence factor in the slope unit and accurately conduct landslide susceptibility assessment.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster risk assessment, and particularly to a landslide susceptibility assessment method and device considering the action intensity of influencing factors. Background Art

[0002] This section aims to provide background or context for the embodiments of the present invention stated in the claims. The description herein is not admitted to be prior art merely by virtue of being included in this section.

[0003] Landslide susceptibility assessment refers to a method of quantitatively assessing the areas and probabilities of landslides by analyzing geological, geomorphic, hydrological, meteorological and other factors affecting the occurrence of landslides. Accurate landslide susceptibility assessment can identify potential landslide risk areas and timely warn of the occurrence of landslide disasters. Therefore, studying landslide susceptibility assessment is of great significance for scientifically formulating disaster prevention and mitigation strategies and protecting people's lives and property.

[0004] Landslide influencing factors are the basis of landslide susceptibility assessment and determine the assessment results. The landslide susceptibility assessment of slope units usually uses the landslide influencing factors extracted from slope units for assessment. However, in the current quantification process of landslide influencing factors in slope units, the mode statistical method and the average value method fail to consider the action intensity of influencing factors on the occurrence of landslides, and fail to accurately determine and extract the key factor characteristics with a large action intensity on the occurrence of landslides. Therefore, accurate landslide susceptibility assessment cannot be carried out, and the accuracy of landslide susceptibility assessment is low. Summary of the Invention

[0005] The embodiments of the present invention provide a landslide susceptibility assessment method considering the action intensity of influencing factors, which is used to consider the action intensity of landslide influencing factors in slope units and accurately carry out landslide susceptibility assessment. The method includes:

[0006] Based on the digital elevation model data of the area to be evaluated, a plurality of slope units and the coordinate range of each slope unit are determined from the area to be evaluated;

[0007] Obtain a plurality of landslide influencing factors within the area to be evaluated;

[0008] Perform interval division processing on each landslide influencing factor within the area to be evaluated to obtain a plurality of landslide influencing factors after interval division processing;

[0009] Quantify the action intensity of each landslide influencing factor after interval division processing on the occurrence of landslides to obtain each landslide influencing factor considering the action intensity;

[0010] According to the coordinate range of each slope unit, determine the landslide impact factors considering the action intensity that fall within each slope unit, and take the landslide impact factor with the maximum action intensity within each slope unit as the current landslide impact factor of the landslide impact factor action intensity within each considered slope unit;

[0011] Input the current landslide impact factors of the landslide impact factor action intensity within multiple considered slope units into the landslide susceptibility assessment model to obtain the landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained based on the relationship sample data between the landslide impact factors of the impact factor action intensity within the historical considered slope units and the landslide susceptibility assessment results.

[0012] An embodiment of the present invention also provides a landslide susceptibility assessment device considering the action intensity of impact factors, which is used to accurately assess the landslide susceptibility by considering the action intensity of the landslide impact factors within the slope unit. The device includes:

[0013] An extraction unit, configured to determine multiple slope units and the coordinate range of each slope unit from the area to be evaluated based on the digital elevation model data of the area to be evaluated;

[0014] An acquisition unit, configured to acquire multiple landslide impact factors within the area to be evaluated;

[0015] An interval division processing unit, configured to perform interval division processing on each landslide impact factor within the area to be evaluated to obtain multiple landslide impact factors after interval division processing;

[0016] An action intensity quantification unit, configured to quantify the action intensity of each landslide impact factor after interval division processing on the occurrence of landslides to obtain each landslide impact factor considering the action intensity;

[0017] A consideration action intensity impact factor determination unit, configured to determine the landslide impact factors considering the action intensity that fall within each slope unit according to the coordinate range of each slope unit, and take the landslide impact factor with the maximum action intensity within each slope unit as the current landslide impact factor of the landslide impact factor action intensity within each considered slope unit;

[0018] A landslide susceptibility assessment unit, configured to input the current landslide impact factors of the landslide impact factor action intensity within multiple considered slope units into the landslide susceptibility assessment model to obtain the landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained based on the relationship sample data between the landslide impact factors of the impact factor action intensity within the historical considered slope units and the landslide susceptibility assessment results.

[0019] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned landslide susceptibility assessment method considering the action intensity of influence factors is implemented.

[0020] An embodiment of the present invention further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the above-mentioned landslide susceptibility assessment method considering the action intensity of influence factors is implemented.

[0021] An embodiment of the present invention further provides a computer program product. The computer program product includes a computer program. When the computer program is executed by a processor, the above-mentioned landslide susceptibility assessment method considering the action intensity of influence factors is implemented.

[0022] Compared with the prior art in which the mode statistical method and the average value method fail to consider the action intensity of influence factors on landslide occurrence when processing landslide influence factor data, thereby affecting the accuracy of landslide susceptibility assessment, the landslide susceptibility assessment solution considering the action intensity of influence factors provided in the embodiments of the present invention can consider the action intensity of landslide influence factors on landslide occurrence within a slope unit, accurately perform landslide susceptibility assessment, and improve the accuracy of landslide susceptibility assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. In the drawings:

[0024] Figure 1 is a schematic flowchart of the landslide susceptibility assessment method considering the action intensity of influence factors in the embodiments of the present invention;

[0025] Figure 2 is a raster map generated by B value in the embodiments of the present invention;

[0026] Figure 3 is a raster map generated by calculating C value in the embodiments of the present invention;

[0027] Figure 4 is the third raster map provided in the embodiments of the present invention;

[0028] Figure 5 is a slope unit extraction result map provided in the embodiments of the present invention;

[0029] Figure 6The landslide influence factor map considering the action intensity provided by the embodiment of the present invention Figure 6 Among them, (a) is the lithology map Figure 6 Among them, (b) is the remote sensing ecological index map Figure 6 Among them, (c) is the soil type map

[0030] Figure 7 The landslide susceptibility assessment result map provided by the embodiment of the present invention

[0031] Figure 8 The structural schematic diagram of the landslide susceptibility assessment device considering the action intensity of influence factors in the embodiment of the present invention Specific implementation manners

[0032] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following further describes the embodiments of the present invention in detail with reference to the drawings. Herein, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but not to limit the present invention

[0033] In the technical solution of this application, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of laws and regulations

[0034] Figure 1 The flow schematic diagram of the landslide susceptibility assessment method considering the action intensity of influence factors in the embodiment of the present invention, as Figure 1 shown, the method includes the following steps

[0035] Step 101: Based on the digital elevation model data of the area to be evaluated, determine multiple slope units from the area to be evaluated, and the coordinate range of each slope unit

[0036] Step 102: Obtain multiple landslide influence factors within the area to be evaluated

[0037] Step 103: Perform interval division processing on each landslide influence factor within the area to be evaluated to obtain multiple landslide influence factors after interval division processing

[0038] Step 104: Quantify the action intensity of each landslide influence factor after interval division processing on the occurrence of landslides to obtain each landslide influence factor considering the action intensity

[0039] Step 105: According to the coordinate range of each slope unit, determine the landslide influence factors considering the action intensity included in each slope unit, and use the landslide influence factor with the maximum action intensity within each slope unit as the current landslide influence factor of the landslide influence factor action intensity within each slope unit considering the slope

[0040] Step 106: Input multiple current landslide influence factors that take into account the action intensity of the landslide influence factors within the slope units into the landslide susceptibility assessment model to obtain the landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained and generated according to the relationship sample data between the landslide influence factors that take into account the action intensity of the influence factors within the historical slope units and the landslide susceptibility assessment result.

[0041] In the landslide susceptibility assessment method that takes into account the action intensity of the influence factors provided in the embodiments of the present invention, during operation: Based on the digital elevation model data of the area to be evaluated, determine multiple slope units from the area to be evaluated, and the coordinate range of each slope unit; obtain multiple landslide influence factors within the area to be evaluated; perform interval division processing on each landslide influence factor within the area to be evaluated to obtain multiple landslide influence factors after interval division processing; quantify the action intensity of each landslide influence factor after interval division processing on the occurrence of landslides to obtain each landslide influence factor that takes into account the action intensity; according to the coordinate range of each slope unit, determine the landslide influence factors that take into account the action intensity included in each slope unit, and use the landslide influence factor with the maximum action intensity within each slope unit as the current landslide influence factor of the landslide influence factor action intensity within each slope unit that takes into account the slope unit; input multiple current landslide influence factors that take into account the landslide influence factor action intensity within the slope units into the landslide susceptibility assessment model to obtain the landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained and generated according to the relationship sample data between the landslide influence factors that take into account the action intensity of the influence factors within the historical slope units and the landslide susceptibility assessment result.

[0042] Compared with the prior art technical solutions in which the mode statistical method and the average value method fail to take into account the action intensity of the influence factors on the occurrence of landslides when processing landslide influence factor data, thereby affecting the accuracy of landslide susceptibility assessment, the landslide susceptibility assessment method that takes into account the action intensity of the influence factors provided in the embodiments of the present invention can take into account the action intensity of the landslide influence factors within the slope units on the occurrence of landslides, accurately perform landslide susceptibility assessment, and improve the accuracy of landslide susceptibility assessment. The landslide susceptibility assessment method that takes into account the action intensity of the influence factors will be introduced in detail below.

[0043] In the quantification process of the existing landslide impact factors of slope units, the mode statistical method and the average value method fail to consider the intensity of the impact of the impact factors on the occurrence of landslides when processing the landslide impact factor data, and fail to accurately determine and extract the key factor characteristics with a large impact intensity on the occurrence of landslides, which will affect the accuracy and credibility of the susceptibility assessment results. Based on this, the present invention provides a landslide susceptibility assessment method that takes into account the intensity of the impact of the impact factors within the slope unit. That is, aiming at the problems existing in the landslide susceptibility assessment of slope units, the purpose of the present invention is to provide a landslide susceptibility assessment method that takes into account the intensity of the impact of the impact factors within the slope unit to solve the problems that the mode statistical method and the average value method fail to consider the intensity of the impact of the impact factors on the occurrence of landslides when processing the landslide impact factor data, and fail to accurately determine and extract the key factor characteristics with a large impact intensity on the occurrence of landslides, which affect the accuracy and credibility of the landslide susceptibility assessment. The following combines the attached Figures 1 to 7 A further detailed description will be given to the embodiments of the present invention.

[0044] First, the steps of pre-training a landslide susceptibility assessment model are introduced.

[0045] In the steps of pre-training a landslide susceptibility assessment model, historical data is used, such as historical landslide impact factor data in the study area and multiple historical slope units determined from the study area.

[0046] In one embodiment, the above-mentioned landslide susceptibility assessment method that takes into account the intensity of the impact of the impact factors may further include pre-training and generating a landslide susceptibility assessment model according to the following method:

[0047] Based on the digital elevation model data of the study area, multiple historical slope units and the coordinate range of each historical slope unit are determined from the study area;

[0048] Obtain multiple historical landslide impact factors in the study area;

[0049] Perform interval division processing on each historical landslide impact factor in the study area to obtain multiple historical landslide impact factors after interval division processing;

[0050] Quantify the intensity of the impact of each historical landslide impact factor after interval division processing on the occurrence of landslides to obtain each historical landslide impact factor that takes into account the intensity of the impact;

[0051] According to the coordinate range of each historical slope unit, determine the historical landslide impact factors that take into account the intensity of the impact and are included in each historical slope unit, and use the landslide impact factor with the largest impact intensity in each historical slope unit as the historical landslide impact factor that takes into account the intensity of the impact of the landslide impact factors within each slope unit;

[0052] Taking the historical landslide influencing factors that take into account the action intensity of the landslide influencing factors within the slope unit and the corresponding historical landslide susceptibility assessment results as relationship sample data to train the landslide susceptibility assessment network, the landslide susceptibility assessment model is obtained.

[0053] Specifically, when implemented, the above method for pre-training and generating the landslide susceptibility assessment model can improve the accuracy of quantifying the action intensity of each landslide influencing factor on the occurrence of landslides, and further improve the accuracy of landslide susceptibility assessment.

[0054] Next, a detailed introduction to the method for training the landslide susceptibility assessment model is given.

[0055] 1. First, introduce the extraction of slope units based on DEM data, that is, based on the digital elevation model data of the study area, multiple historical slope units are determined from the study area, as well as the coordinate range of each historical slope unit.

[0056] The method for extracting slope units based on DEM data may include the following steps:

[0057] (1) Based on the DEM data, for each grid cell, compare the value of the current cell with the difference between its preset number of, for example, 8 neighboring cells, denoted as A (the difference between the value of the current grid cell and the values of the preset number of grid cells adjacent to the current grid cell). Select the neighboring cell with the largest A as the flow direction of the grid cell, and repeat the operation to assign a flow value to each cell, denoted as B (flow value); then generate a grid map (the first grid map) according to the B value of each cell, as Figure 2 shown, Figure 2 is a grid map generated by the B value provided in the embodiment of the present invention.

[0058] (2) Assign an aggregation value to all cells, denoted as C (aggregation value), the initial value of C is 0, according to Figure 2 (the first grid map) traverse each cell in reverse to check its B value. If the B value of the current cell points to one of the adjacent cells, then add 1 to the C of the current cell as the C value of the adjacent cell being pointed to, and repeat this process to complete the calculation of the C value of all cells, thereby generating a grid map (the second grid map), as Figure 3 shown, Figure 3 is a grid map generated by the C value calculation provided in the embodiment of the present invention.

[0059] (3) Then set a threshold (preset aggregation threshold), and set all cells in Figure 3 (the second grid map) with C values greater than the threshold as D. Use Figure 2 (the first grid map) to link all cells of D to generate network e. And starting from the cell with C = 0, use Figure 2The first raster map and the network e are linked in the B - value direction to generate a raster map f (the third raster map), as Figure 4 shown, Figure 4 which is the third raster map provided by the embodiment of the present invention. The raster - to - polygon tool is used to convert f into a surface, denoted as g, to obtain multiple preliminary slope unit surfaces.

[0060] (4) Then, the maximum value in the DEM data is subtracted from each pixel of the DEM data to obtain the inverted DEM data. After that, the inverted f - surface is calculated according to the above steps and denoted as h.

[0061] (5) g and h are merged, and the unreasonable pixels with too small area, broken shape or overly elongated shape that affect the integrity and continuity of the slope unit are corrected to generate a more refined optimized slope unit, thereby obtaining the slope unit i, where i represents the serial number of the slope unit, as Figure 5 shown, Figure 5 which is a slope unit extraction result map provided by the embodiment of the present invention.

[0062] In one embodiment, based on the digital elevation model data of the study area, multiple historical slope units are determined from the study area, and the coordinate range of each historical slope unit may include:

[0063] Based on the digital elevation model data of the area to be evaluated, for each raster pixel in the area to be evaluated, the following operations for determining the flow direction value of each raster pixel and the corresponding first raster map are performed: compare the value of the current raster pixel with the differences in the values of a preset number of adjacent raster pixels of the current raster pixel; select the adjacent raster pixel with the largest difference as the flow direction of the current raster pixel, assign a flow direction value to the current raster pixel; generate the first raster map according to the flow direction values of each raster pixel;

[0064] Based on the first raster map, for each raster pixel in the area to be evaluated, the following operations for determining the agglomeration value of each raster pixel and the corresponding second raster map are performed: assign an agglomeration value to each raster pixel, the initial value of the agglomeration value is 0, traverse each raster pixel in reverse according to the first raster map to check the flow direction value of the current raster pixel. If the flow direction corresponding to the flow direction value of the current raster pixel points to one of the adjacent raster pixels adjacent to the current raster pixel, add 1 to the agglomeration value of the current raster pixel as the agglomeration value of the adjacent raster pixel being pointed to, until the agglomeration values of all raster pixels are determined, and generate the second raster map according to the agglomeration values of each raster pixel;

[0065] Assign a preset label to all raster cells in the second raster map whose agglomeration values are greater than a preset agglomeration threshold. Use the first raster map to link all raster cells labeled with the preset label to generate a network. Starting from the raster cell with an agglomeration value of 0, use the first raster map and the network to link and generate a third raster map according to the flow direction, and convert the third raster map into a surface;

[0066] Subtract each raster cell of the digital elevation model data from the maximum value in the digital elevation model data to obtain inverted digital elevation model data. According to the inverted digital elevation model data, obtain an inverted surface;

[0067] Merge the surface and the inverted surface to obtain multiple slope units and the coordinate range of each slope unit.

[0068] In specific implementation, the above method for determining multiple historical slope units from the study area can improve the extraction accuracy of slope units.

[0069] In one embodiment, merging the surface and the inverted surface to obtain multiple historical slope units may include: merging the surface and the inverted surface, and correcting unreasonable raster cells whose areas affecting the integrity and continuity of slope units are less than a preset area threshold, the degree of shape fragmentation exceeds a preset fragmentation threshold, or the elongation exceeds a preset elongation threshold, to obtain multiple historical slope units.

[0070] In specific implementation, the above method for correcting unreasonable raster cells can improve the extraction accuracy of slope units.

[0071] In one embodiment, the preset number range of raster cells may be from 6 to 10. Preferably, the preset number of raster cells may be 8, which can improve the extraction accuracy of slope units.

[0072] 2. Secondly, introduce obtaining environmental impact factor data related to landslide occurrence in the study area from aspects such as topography, geology, hydrology, and humanities, such as lithology impact factors, remote sensing ecological index impact factors, or soil type impact factors, that is, multiple types of landslide impact factors. Unify the coordinates of the landslide impact factors and use the vector shape elements of the area to be evaluated to extract them, obtaining landslide impact factors that are consistent with the spatial coordinates and shape sizes of the area to be evaluated, that is, the above-mentioned obtaining multiple historical landslide impact factors in the study area, specifically including:

[0073] The impact factor data is resampled, and its resolution is unified to 30 meters before projection transformation. The vector shape of the study area (in the subsequent application of the model for real-time evaluation, the study area in this section can be changed to the area to be evaluated) is used to perform mask extraction on the raster landslide impact factor after projection transformation to obtain landslide impact factors with consistent range size and corresponding spatial position; that is, based on the polygonal elements of the study area, the pixels in the target data set that fall within the study area or intersect with the polygonal elements are retained, and other pixels outside the range are eliminated to obtain the landslide impact factors after pre-operation. All landslide impact factors are subjected to the same operation, and finally a set of landslide impact factors with consistent range size and corresponding spatial position is obtained to improve the accuracy of subsequent modeling.

[0074] 3. Next, the interval division process of the landslide impact factor after the previous step of pre-operation is introduced, that is, the impact factor of each type of historical landslide after the interval division process is obtained, and the interval division process of the landslide impact factor is carried out, specifically including:

[0075] (1) Discrete landslide influencing factors are divided into intervals according to their different categories, that is, discrete geological lithology factors, soil category factors, and land use factors are divided into intervals according to their categories (types).

[0076] (2) For continuous landslide influencing factors, first divide them into several preliminary intervals and sort them from small to large. Each interval contains only one data value, and the interval is denoted as u. The frequency of landslide and non-landslide in each interval is calculated based on the landslide and non-landslide data, denoted as P uj ; j is the two categories of landslide and non-landslide, which can be recorded as P u1 and P u2 Calculate the total number of landslide and non-landslide samples and record it as C j , which can be recorded as C1 and C2 in detail; calculate the total number of landslide and non-landslide samples in each interval, recorded as R u ; Calculate the total number of samples in all intervals as N, and then calculate R u With C j The quotient of the product of and N (the third quotient) is denoted as M uj ; Finally, calculate each interval ui (P uj With M uj The sum of squares of the differences between uj The quotient (the fourth quotient) is denoted by X u When the X of two intervals u (The fourth quotient) can be added to be greater than the X before addition. uIf the (fourth quotient) is large, merge it; otherwise, do not merge it. The newly merged interval will become a new candidate interval. Repeat the above steps until the X value after merging is greater than the preset threshold. Eventually, a set of non-mergable intervals will be obtained, thus completing the intervalization process of the continuous landslide influencing factors.

[0077] 4. Again, introduce the method of quantifying the influence intensity of landslide influencing factors on landslide occurrence, that is, quantify the influence intensity of each type of historical landslide influencing factor after the interval division process on landslide occurrence, and obtain each type of historical landslide influencing factor considering the influence intensity. The specific methods for quantifying the influence intensity of landslide influencing factors on landslide occurrence include:

[0078] Determine the number of landslide points in different intervals of a single landslide influencing factor after the above-mentioned intervalization is completed, denoted as N u , and denote the area of different intervals as S u , calculate N u and S u The quotient of N and S is denoted as J. Next, count the number of landslide points in the entire study area, denoted as N; the total area of the influencing factors, denoted as S; calculate the quotient of N and S, denoted as K. Finally, the quotient of J and K is calculated and the logarithm (ln) is taken, and the obtained value is denoted as L. L is the influence intensity of the influencing factor on landslide occurrence.

[0079] In one embodiment, quantifying the historical influence intensity of each historical landslide influencing factor after the interval division process on landslide occurrence, and obtaining each historical landslide influencing factor considering the influence intensity may include:

[0080] Determine the number of landslide points in different intervals of each landslide influencing factor, and the area of different intervals of each landslide influencing factor;

[0081] Determine the first quotient of the number of landslides in different intervals of each landslide influencing factor and the area of different intervals;

[0082] Determine the number of landslide points in the entire study area, and the total area of all influencing factors in the entire study area;

[0083] Determine the second quotient of the number of landslide points in the entire study area and the total area of all influencing factors in the entire study area;

[0084] Obtain the quotient of the first quotient and the second quotient and take the logarithm as the influence intensity of each landslide influencing factor on landslide occurrence, associate each influence intensity with the corresponding landslide influencing factor, and obtain each landslide influencing factor considering the influence intensity.

[0085] In specific implementation, quantifying the action intensity of each landslide influence factor on landslide occurrence to obtain each landslide influence factor considering the action intensity can improve the accuracy of quantifying the action intensity of each landslide influence factor on landslide occurrence, and further improve the accuracy of landslide susceptibility assessment.

[0086] 5. Again, introduce determining the historical landslide influence factors considering the action intensity of the types included in each historical slope unit according to the coordinate range of each historical slope unit, and taking the landslide influence factor with the maximum action intensity in each historical slope unit as the historical landslide influence factor considering the action intensity of the landslide influence factor in each slope unit:

[0087] Assign the attribute value of the influence factor with a large action intensity to each corresponding slope unit, that is, each slope unit has an action intensity value, denoted as X （max,i） . Then perform the same operation on all slope units and landslide influence factors, thereby generating the historical landslide influence factors considering the action intensity of the landslide influence factor in each slope unit. Figure 6 For the multiple types of landslide influence factor maps considering the action intensity provided by the present invention, Figure 6 in (a) is the lithology map, Figure 6 in (b) is the remote sensing ecological index map, Figure 6 in (c) is the soil type map, X （max,i） = max ( X i1 ,X i2 ,......X im ), where m represents the m-th action intensity value included in slope unit i.

[0088] 6. Finally, introduce applying the landslide influence factor considering the action intensity to a machine learning model, training with a training data set, and conducting landslide susceptibility assessment, that is, training to obtain a landslide susceptibility assessment model for landslide susceptibility assessment. Using the multiple types of historical landslide influence factors considering the action intensity of the landslide influence factor in the slope unit and the corresponding historical landslide susceptibility assessment results as relationship sample data to train the landslide susceptibility assessment network, obtaining the landslide susceptibility assessment model. When specifically testing the model or validating the model, the landslide influence factor considering the action intensity (the historical landslide influence factor considering the action intensity of the landslide influence factor in the slope unit) can be used as the input quantity of the landslide susceptibility assessment model, using 0 and 1 as labels, and the value output will be a value between 0 and 1 (historical landslide susceptibility assessment result). The closer the value is to 1, the greater the possibility of landslide occurrence in this area. Figure 7 For the landslide susceptibility assessment result map provided by the embodiment of the present invention.

[0089] Second, the steps for performing real-time landslide susceptibility assessment on the area to be evaluated by using the above-mentioned pre-trained landslide susceptibility assessment model, i.e., the above steps 101 to 106, are introduced. Among them:

[0090] In one embodiment, in the above step 101, based on the digital elevation model data of the area to be evaluated, determining a plurality of slope units from the area to be evaluated, and the coordinate range of each slope unit may include:

[0091] Based on the digital elevation model data of the area to be evaluated, for each grid cell in the area to be evaluated, perform the following operations to determine the flow direction value of each grid cell and the corresponding first grid map: compare the value of the current grid cell with the differences in the values of a preset number of adjacent grid cells of the current grid cell; select the adjacent grid cell with the largest difference as the flow direction of the current grid cell, assign a flow direction value to the current grid cell; generate the first grid map according to the flow direction values of each grid cell;

[0092] Based on the first grid map, for each grid cell in the area to be evaluated, perform the following operations to determine the accumulation value of each grid cell and the corresponding second grid map: assign an accumulation value to each grid cell, the initial value of the accumulation value is 0, traverse each grid cell in reverse according to the first grid map to check the flow direction value of the current grid cell. If the flow direction corresponding to the flow direction value of the current grid cell points to one of the adjacent grid cells adjacent to the current grid cell, add 1 to the accumulation value of the current grid cell as the accumulation value of the adjacent grid cell pointed to, until the accumulation values of all grid cells are determined, and generate the second grid map according to the accumulation values of each grid cell;

[0093] Assign a preset mark to all grid cells in the second grid map with accumulation values greater than the preset accumulation threshold, use the first grid map to link all grid cells marked with the preset mark to generate a network, start from the grid cell with an accumulation value of 0, use the first grid map and the network to link according to the flow direction to generate a third grid map, and convert the third grid map into a surface;

[0094] Subtract the maximum value in the digital elevation model data from each grid cell of the digital elevation model data to obtain the inverted digital elevation model data, and obtain the inverted surface according to the inverted digital elevation model data;

[0095] Merge the surface and the inverted surface to obtain a plurality of slope units and the coordinate range of each slope unit.

[0096] Specifically, the above method for determining a plurality of slope units from the area to be evaluated can improve the extraction accuracy of slope units.

[0097] In one embodiment, the surface and the inverted surface are merged to obtain a slope unit, including: merging the surface and the inverted surface, and correcting the unreasonable grid cells that affect the integrity and continuity of the slope unit, where the area is less than a preset area threshold, the degree of shape fragmentation exceeds a preset fragmentation threshold, or the elongation exceeds a preset elongation threshold, to obtain a plurality of slope units.

[0098] Specifically, the method of correcting the unreasonable grid cells above can improve the extraction accuracy of slope units.

[0099] In one embodiment, the preset number range of the grid cells can be from 6 to 10, preferably 8, which can improve the extraction accuracy of slope units.

[0100] In one embodiment, in step 102 above, the step of obtaining multiple landslide influencing factors within the area to be evaluated can refer to the introduction in "2" of "One" above.

[0101] In one embodiment, in step 103 above, quantifying the action intensity of each landslide influencing factor on landslide occurrence after interval division processing to obtain each landslide influencing factor considering the action intensity may include:

[0102] Determining the number of landslide points in different intervals of each landslide influencing factor, and the area in different intervals of each landslide influencing factor;

[0103] Determining the first quotient of the number of landslides in different intervals of each landslide influencing factor and the area in different intervals;

[0104] Determining the total number of landslide points in the entire area to be evaluated, and the total area of all influencing factors in the entire area to be evaluated;

[0105] Determining the second quotient of the total number of landslide points in the entire area to be evaluated and the total area of all influencing factors in the entire area to be evaluated;

[0106] Calculating the quotient of the first quotient and the second quotient and taking the logarithm as the action intensity of each landslide influencing factor on landslide occurrence, and associating each action intensity with the corresponding landslide influencing factor to obtain each landslide influencing factor considering the action intensity.

[0107] Specifically, quantifying the action intensity of each landslide influencing factor on landslide occurrence to obtain each landslide influencing factor considering the action intensity can improve the accuracy of quantifying the action intensity of each landslide influencing factor on landslide occurrence, and further improve the accuracy of landslide susceptibility assessment.

[0108] Each step of the above landslide susceptibility assessment of the area to be evaluated can refer to the implementation of the steps of the above pre-trained landslide susceptibility assessment model.

[0109] The beneficial effects of the landslide susceptibility assessment method considering the action intensity of influencing factors provided by the embodiments of the present invention are as follows: The embodiments of the present invention use UAV data and remote sensing data as data sources to construct a landslide susceptibility assessment method that can consider the action intensity of influencing factors within slope units. The landslide influencing factors quantified by this method can fully consider the action intensity of influencing factors on the occurrence of landslides, accurately determine and extract the key factor characteristics with a large action intensity on the occurrence of landslides, and provide a data basis for the accurate assessment of landslide susceptibility. Combining the landslide influencing factors considering the action intensity with a machine learning model to evaluate landslide susceptibility, the results have high accuracy, can accurately and clearly evaluate the risk level and spatial location of landslide disasters in the study area, and have important practical significance for geological disaster warning and disaster prevention and mitigation.

[0110] In the embodiments of the present invention, a landslide susceptibility assessment device considering the action intensity of influencing factors is also provided, as described in the following embodiments. Since the principle of the device to solve problems is similar to that of the landslide susceptibility assessment method considering the action intensity of influencing factors, the implementation of the device can refer to the implementation of the landslide susceptibility assessment method considering the action intensity of influencing factors, and the repeated parts will not be described again.

[0111] Figure 8 It is a schematic structural diagram of the landslide susceptibility assessment device considering the action intensity of influencing factors in the embodiments of the present invention, as Figure 8 shown. The device includes:

[0112] An extraction unit 01, configured to determine a plurality of slope units and the coordinate range of each slope unit from the area to be evaluated based on the digital elevation model data of the area to be evaluated;

[0113] An acquisition unit 02, configured to acquire a plurality of landslide influencing factors within the area to be evaluated;

[0114] An interval division processing unit 03, configured to perform interval division processing on each landslide influencing factor within the area to be evaluated to obtain a plurality of landslide influencing factors after interval division processing;

[0115] An action intensity quantification unit 04, configured to quantify the action intensity of each landslide influencing factor after interval division processing on the occurrence of landslides to obtain each landslide influencing factor considering the action intensity;

[0116] A landslide influencing factor determination unit 05 considering the action intensity, configured to determine the landslide influencing factors considering the action intensity included in each slope unit according to the coordinate range of each slope unit, and use the landslide influencing factor with the largest action intensity within each slope unit as the current landslide influencing factor of the action intensity of the landslide influencing factors within each slope unit;

[0117] The landslide susceptibility assessment unit 06 is used to input multiple current landslide impact factors that take into account the action intensity of landslide impact factors within the slope units into the landslide susceptibility assessment model to obtain the landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained and generated according to the relationship sample data between the landslide impact factors that take into account the action intensity of impact factors within the historical slope units and the landslide susceptibility assessment results.

[0118] In one embodiment, the above extraction unit can specifically be used for:

[0119] Based on the digital elevation model data of the area to be evaluated, for each grid cell within the area to be evaluated, perform the following operations to determine the flow direction value of each grid cell and the corresponding first grid map: compare the value of the current grid cell with the differences in the values of a preset number of adjacent grid cells of the current grid cell; select the adjacent grid cell with the largest difference as the flow direction of the current grid cell, and assign a flow direction value to the current grid cell; generate the first grid map according to the flow direction values of each grid cell;

[0120] Based on the first grid map, for each grid cell within the area to be evaluated, perform the following operations to determine the accumulation value of each grid cell and the corresponding second grid map: assign an accumulation value to each grid cell, the initial value of the accumulation value is 0, traverse each grid cell in reverse according to the first grid map to check the flow direction value of the current grid cell. If the flow direction corresponding to the flow direction value of the current grid cell points to one of the adjacent grid cells adjacent to the current grid cell, add 1 to the accumulation value of the current grid cell as the accumulation value of the adjacent grid cell being pointed to, until the accumulation values of all grid cells are determined, and generate the second grid map according to the accumulation values of each grid cell;

[0121] Assign a preset mark to all grid cells in the second grid map with accumulation values greater than the preset accumulation threshold, use the first grid map to link all grid cells marked with the preset mark to generate a network, start from the grid cell with an accumulation value of 0, use the first grid map and the network to link according to the flow direction to generate the third grid map, and convert the third grid map into a surface;

[0122] Subtract the maximum value in the digital elevation model data from each grid cell of the digital elevation model data to obtain the inverted digital elevation model data, and obtain the inverted surface according to the inverted digital elevation model data;

[0123] Merge the surface and the inverted surface to obtain multiple slope units and the coordinate range of each slope unit.

[0124] In one embodiment, the surface and the inverted surface are combined to obtain a slope unit, including: combining the surface and the inverted surface, and correcting the unreasonable grid pixels whose areas are less than a preset area threshold, whose shape fragmentation degree exceeds a preset fragmentation threshold, or whose elongation exceeds a preset elongation threshold and affect the integrity and continuity of the slope unit, to obtain a plurality of slope units.

[0125] In one embodiment, the preset number range of the grid pixels can be from 6 to 10.

[0126] In one embodiment, the above-mentioned action intensity quantification unit can specifically be used for:

[0127] Determine the number of landslide points in different intervals of each landslide influencing factor, and the area in different intervals of each landslide influencing factor;

[0128] Determine the first quotient of the number of landslides in different intervals of each landslide influencing factor and the area in different intervals;

[0129] Determine the number of landslide points in the entire area to be evaluated, and the total area of all influencing factors in the entire area to be evaluated;

[0130] Determine the second quotient of the number of landslide points in the entire area to be evaluated and the total area of all influencing factors in the entire area to be evaluated;

[0131] Obtain the quotient of the first quotient and the second quotient and take the logarithm, as the action intensity of each landslide influencing factor on the occurrence of landslides, and associate each action intensity with the corresponding landslide influencing factor to obtain each landslide influencing factor taking into account the action intensity.

[0132] In one embodiment, the landslide susceptibility assessment device considering the action intensity of influencing factors provided by the embodiments of the present invention may further include a training unit, which is used to pre-train and generate a landslide susceptibility assessment model according to the following method:

[0133] Based on the digital elevation model data of the study area, determine a plurality of historical slope units from the study area, and the coordinate range of each historical slope unit;

[0134] Obtain a plurality of historical landslide influencing factors in the study area;

[0135] Perform interval division processing on each historical landslide influencing factor in the study area to obtain a plurality of historical landslide influencing factors after interval division processing;

[0136] Quantify the action intensity of each historical landslide influencing factor after interval division processing on the occurrence of landslides to obtain each historical landslide influencing factor taking into account the action intensity;

[0137] According to the coordinate range of each historical slope unit, determine the historical landslide influence factors considering the action intensity that fall within each historical slope unit, and use the landslide influence factor with the maximum action intensity within each historical slope unit as the historical landslide influence factor of the landslide influence factor action intensity within each considered slope unit;

[0138] Use the historical landslide influence factor of the landslide influence factor action intensity within the considered slope unit and the corresponding historical landslide susceptibility assessment results as relationship sample data to train the landslide susceptibility assessment network, and obtain the landslide susceptibility assessment model.

[0139] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned landslide susceptibility assessment method considering the action intensity of influence factors.

[0140] An embodiment of the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned landslide susceptibility assessment method considering the action intensity of influence factors.

[0141] An embodiment of the present invention also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the above-mentioned landslide susceptibility assessment method considering the action intensity of influence factors.

[0142] In the embodiment of the present invention, the landslide susceptibility assessment scheme considering the action intensity of influence factors, compared with the prior art technical schemes of the mode statistical method and the average value method that fail to consider the action intensity of influence factors on landslide occurrence when processing landslide influence factor data, and thus affect the accuracy of landslide susceptibility assessment, can consider the action intensity of landslide influence factors within the slope unit on landslide occurrence, accurately conduct landslide susceptibility assessment, and improve the accuracy of landslide susceptibility assessment.

[0143] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0144] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one or more flows and / or blocks. Figure 1 in one or more flows and / or blocks Figure 1 or in one or more blocks.

[0145] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one or more flows and / or blocks. Figure 1 in one or more flows and / or blocks Figure 1 or in one or more blocks.

[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows and / or blocks. Figure 1 in one or more flows and / or blocks Figure 1 or in one or more blocks.

[0147] The specific embodiments described above further elaborate on the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A landslide susceptibility assessment method considering the action intensity of influencing factors, characterized in that, Including: Based on the digital elevation model data of the area to be evaluated, multiple slope units are determined from the area to be evaluated, and the coordinate range of each slope unit, which includes: based on the digital elevation model data of the area to be evaluated, for each grid cell in the area to be evaluated, perform the following operations to determine the flow direction value of each grid cell and the corresponding first grid map: compare the value of the current grid cell with the differences in the values of a preset number of adjacent grid cells of the current grid cell; select the adjacent grid cell with the largest difference as the flow direction of the current grid cell, and assign a flow direction value to the current grid cell; generate the first grid map according to the flow direction values of each grid cell. Obtain multiple landslide influencing factors within the area to be evaluated. Perform interval division processing on each landslide impact factor within the area to be evaluated, obtaining multiple landslide impact factors after the interval division processing; among them, the interval division processing for continuous landslide impact factors includes the following steps: divide the continuous landslide impact factor into several preliminary intervals, sort the several preliminary intervals from smallest to largest, each interval contains only one data value, and the interval is denoted as ui; calculate the frequencies of landslides and non-landslides in each interval, denoted as P uj , where the frequency of landslides is denoted as P u1 , and the frequency of non-landslides is denoted as P u2 ; calculate the total number of samples of landslides and non-landslides, denoted as C j , where the total number of landslide samples is denoted as C1, and the total number of non-landslide samples is denoted as C2; calculate the total number of landslide and non-landslide samples in each interval, denoted as R u ; calculate the total number of samples of all intervals, denoted as N, and calculate the product of R u and C j , and denote the third quotient of the product and N as M uj ; calculate the sum of the squares of the differences between P uj and M uj in each interval ui, and denote the fourth quotient of the sum of squares and M uj as X u ; if the sum of the fourth quotients of two intervals is greater than the fourth quotient before addition, then merge them, otherwise do not merge. The newly merged interval will become a new candidate interval. Repeat the above steps until the fourth quotient after merging is greater than the preset threshold. Finally, a set of non-mergable intervals will be obtained, thus completing the interval division processing of continuous landslide impact factors; Quantify the action intensity of each landslide influencing factor after interval division processing on landslide occurrence, and obtain each landslide influencing factor considering the action intensity. According to the coordinate range of each slope unit, determine the landslide influencing factors considering the action intensity included in each slope unit, and take the landslide influencing factor with the largest action intensity within each slope unit as the current landslide influencing factor of the landslide influencing factor action intensity within each slope unit considering the slope. Input the current landslide influencing factors of the landslide influencing factor action intensity within multiple slope units considering the slope into the landslide susceptibility assessment model to obtain the landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained and generated according to the relationship sample data between the landslide influencing factors of the historical slope unit considering the influence factor action intensity and the landslide susceptibility assessment result.

2. The method according to claim 1, characterized in that, Based on the digital elevation model data of the area to be evaluated, determining multiple slope units from the area to be evaluated, and the coordinate range of each slope unit, further includes: Based on the first grid map, for each grid cell in the area to be evaluated, perform the following operations to determine the agglomeration value of each grid cell and the corresponding second grid map: assign an agglomeration value to each grid cell, the initial value of the agglomeration value is 0, traverse each grid cell in reverse according to the first grid map to check the flow direction value of the current grid cell. If the flow direction corresponding to the flow direction value of the current grid cell points to one of the adjacent grid cells adjacent to the current grid cell, add 1 to the agglomeration value of the current grid cell as the agglomeration value of the adjacent grid cell being pointed to, until the agglomeration values of all grid cells are determined, and generate the second grid map according to the agglomeration values of each grid cell. Assign a preset mark to all grid cells in the second grid map with agglomeration values greater than the preset agglomeration threshold, use the first grid map to link all grid cells marked with the preset mark to generate a network, start from the grid cell with an agglomeration value of 0, use the first grid map and the network to link according to the flow direction to generate a third grid map, and convert the third grid map into a surface. Subtract the maximum value in the digital elevation model data from each grid cell of the digital elevation model data to obtain the inverted digital elevation model data, and obtain the inverted surface according to the inverted digital elevation model data. Merge the surface and the inverted surface to obtain multiple slope units and the coordinate range of each slope unit.

3. The method according to claim 2, wherein Merge the surface and the inverted surface to obtain multiple slope units, including: merging the surface and the inverted surface, and correcting unreasonable grid cells with an area smaller than a preset area threshold, a shape fragmentation degree exceeding a preset fragmentation threshold, or an elongation exceeding a preset elongation threshold that affect the integrity and continuity of the slope units, to obtain multiple slope units.

4. The method according to claim 2, characterized in that, The preset number range of the grid cells is from 6 to 10.

5. The method according to claim 1, wherein Quantify the action intensity of each landslide influencing factor on landslide occurrence after interval division processing to obtain each landslide influencing factor considering the action intensity, including: Determine the number of landslide points in different intervals of each landslide influencing factor, and the area of different intervals of each landslide influencing factor; Determine the first quotient of the number of landslides in different intervals of each landslide influencing factor and the area of different intervals; Determine the number of landslide points in the entire area to be evaluated, and the total area of all influencing factors in the entire area to be evaluated; Determine the second quotient of the number of landslide points in the entire area to be evaluated and the total area of all influencing factors in the entire area to be evaluated; Obtain the quotient of the first quotient and the second quotient and take the logarithm as the action intensity of each landslide influencing factor on landslide occurrence, and associate each action intensity with the corresponding landslide influencing factor to obtain each landslide influencing factor considering the action intensity.

6. The method according to claim 1, wherein It also includes pre-training and generating a landslide susceptibility assessment model according to the following method: Based on the digital elevation model data of the study area, determine multiple historical slope units from the study area, and the coordinate range of each historical slope unit; Obtain multiple historical landslide influencing factors in the study area; Perform interval division processing on each historical landslide influencing factor in the study area to obtain multiple historical landslide influencing factors after interval division processing; Quantify the action intensity of each historical landslide influencing factor on landslide occurrence after interval division processing to obtain each historical landslide influencing factor considering the action intensity; According to the coordinate range of each historical slope unit, determine the historical landslide influencing factors considering the action intensity included in each historical slope unit, and use the landslide influencing factor with the maximum action intensity in each historical slope unit as the historical landslide influencing factor of the landslide influencing factor action intensity in each slope unit considering the action intensity; Use the historical landslide influencing factor of the landslide influencing factor action intensity in the slope unit considering the action intensity and the corresponding historical landslide susceptibility assessment result as relationship sample data to train the landslide susceptibility assessment network to obtain the landslide susceptibility assessment model.

7. A landslide susceptibility assessment device that takes into account the intensity of the influence factor, characterized in that, It includes: An extraction unit, configured to determine multiple slope units from the area to be evaluated based on the digital elevation model data of the area to be evaluated, and the coordinate range of each slope unit, which includes: based on the digital elevation model data of the area to be evaluated, for each grid cell in the area to be evaluated, perform the following operations to determine the flow direction value of each grid cell and the corresponding first grid map: compare the value of the current grid cell with the difference in the values of a preset number of adjacent grid cells of the current grid cell; select the adjacent grid cell with the largest difference as the flow direction of the current grid cell, and assign a flow direction value to the current grid cell; generate a first grid map according to the flow direction value of each grid cell. An acquisition unit for acquiring a plurality of landslide influencing factors within the area to be evaluated; An interval division processing unit is used to perform interval division processing on each landslide impact factor in the area to be evaluated, and obtain multiple landslide impact factors after interval division processing. Among them, the interval processing of continuous landslide impact factors includes the following steps: divide the continuous landslide impact factor into several preliminary intervals, sort the several preliminary intervals from small to large, each interval contains only one data value, and the interval is denoted as ui; calculate the frequencies of landslides and non-landslides in each interval, denoted as P uj , where the frequency of landslides is denoted as P u1 , and the frequency of non-landslides is denoted as P u2 , calculate the total number of samples of landslides and non-landslides, denoted as C j , where the total number of landslide samples is denoted as C1, and the total number of non-landslide samples is denoted as C2; calculate the total number of landslide and non-landslide samples in each interval, denoted as R u ; calculate the total number of samples of all intervals, denoted as N, and calculate the product of R u and C j , and the third quotient of the product and N is denoted as M uj ; calculate the sum of the squares of the differences between P uj and M uj in each interval ui, and the fourth quotient of the sum of the squares and M uj , denoted as X u ; if the sum of the fourth quotients of two intervals is larger than the fourth quotient before addition, then merge them, otherwise do not merge. The merged new interval will become a new candidate interval. Repeat the above steps until the fourth quotient after merging is greater than the preset threshold. Finally, a set of non-mergable intervals will be obtained, thus completing the interval processing of continuous landslide impact factors; An action intensity quantification unit for quantifying the action intensity of each landslide influencing factor after interval division processing on the occurrence of landslides, to obtain each landslide influencing factor taking into account the action intensity; A landslide influencing factor determination unit taking into account the action intensity for determining, according to the coordinate range of each slope unit, the landslide influencing factors taking into account the action intensity included in each slope unit, and taking the landslide influencing factor with the maximum action intensity within each slope unit as the current landslide influencing factor of the action intensity of the landslide influencing factor within each slope unit taking into account the slope unit; A landslide susceptibility assessment unit for inputting the current landslide influencing factors of the action intensity of the landslide influencing factors within a plurality of slope units taking into account the slope unit into a landslide susceptibility assessment model to obtain a landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained and generated according to the relationship sample data between the landslide influencing factors of the action intensity of the influencing factors within the historical slope unit taking into account the slope unit and the landslide susceptibility assessment result.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the method according to any one of claims 1 to 6.

Images