Landslide susceptibility evaluation method and device considering influence factor action intensity

Abstract

The invention discloses a landslide susceptibility assessment method and device considering influence factor action intensity. The method comprises the following steps: determining a plurality of slope units from a to-be-assessed region based on digital elevation model data; performing interval division processing on the plurality of landslide influence factors in the to-be-evaluated area; quantifying the action intensity of each landslide influence factor on the occurrence of the landslide after interval division processing; according to the coordinate range of each slope unit, determining a landslide influence factor which is divided into each slope unit and takes the action intensity into consideration, and taking the landslide influence factor with the maximum action intensity in each slope unit as a factor which takes the action intensity of the landslide influence factor in each current slope unit into consideration; and inputting a plurality of factors which currently consider the action intensity of the landslide influence factors in the slope unit into the landslide susceptibility evaluation model to obtain a landslide susceptibility evaluation result. According to the method, the action intensity of the landslide influence factors in the slope units on the occurrence of the landslide can be considered, and the landslide susceptibility can be accurately evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster risk assessment, and in particular to a landslide susceptibility assessment method and device taking into account the intensity of influencing factors. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] Landslide susceptibility assessment refers to a method of quantitatively evaluating the area and probability of landslides by analyzing the geological, geomorphological, hydrological, and meteorological factors that affect the occurrence of landslides. Accurate landslide susceptibility assessment can identify potential landslide risk areas and timely warn of landslide disasters. Therefore, the study of landslide susceptibility assessment is of great significance for the scientific formulation of disaster prevention and mitigation strategies and the protection of people's lives and property.

[0004] Landslide influencing factors are the basis of landslide susceptibility assessment and determine the results of the assessment. Slope unit landslide susceptibility assessment is usually performed using landslide influencing factors extracted from slope units. However, in the current process of quantifying landslide influencing factors in slope units, the majority statistics method and the average method fail to take into account the intensity of the influencing factors on landslide occurrence when processing landslide influencing factor data, and fail to accurately determine and extract the key factor characteristics with a high intensity of landslide occurrence. Therefore, it is impossible to accurately perform landslide susceptibility assessment, and the accuracy of landslide susceptibility assessment is low. Summary of the invention

[0005] The embodiment of the present invention provides a landslide susceptibility assessment method taking into account the intensity of the influence factors, which is used to take into account the intensity of the influence of the landslide influence factors in the slope unit on the occurrence of the landslide and accurately perform the landslide susceptibility assessment. The method includes: Based on the digital elevation model data of the area to be evaluated, a plurality of slope units and a coordinate range of each slope unit are determined from the area to be evaluated; Obtain multiple landslide impact factors in the area to be assessed; Perform interval division processing on each landslide impact factor in the area to be assessed, and obtain multiple landslide impact factors after interval division processing; The intensity of each landslide influencing factor on the occurrence of landslide after the quantified interval division is obtained to obtain each landslide influencing factor taking into account the intensity of the action; According to the coordinate range of each slope unit, determine the landslide impact factor considering the action intensity included in each slope unit, and take the landslide impact factor with the largest action intensity in each slope unit as the current landslide impact factor considering the action intensity of the landslide impact factor in each slope unit; A plurality of current landslide influencing factors taking into account the intensity of the landslide influencing factors within the slope unit are input into a landslide susceptibility assessment model to obtain a landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained and generated based on sample data of the relationship between the landslide influencing factors taking into account the intensity of the influencing factors within the slope unit and the landslide susceptibility assessment results.

[0006] The embodiment of the present invention further provides a landslide susceptibility assessment device taking into account the strength of the influencing factors, which is used to take into account the strength of the landslide influencing factors in the slope unit on the occurrence of landslides and accurately perform landslide susceptibility assessment. The device includes: An extraction unit is used to determine a plurality of slope units and a 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; An acquisition unit, used for acquiring a plurality of landslide impact factors in the area to be assessed; An interval division processing unit is used to perform interval division processing on each landslide impact factor in the area to be assessed, and obtain multiple landslide impact factors after the interval division processing; The action intensity quantification unit is used to quantify the action intensity of each landslide influencing factor on the occurrence of landslide after the interval division process, and obtain each landslide influencing factor taking into account the action intensity; The unit for determining the influence factor taking into account the intensity of action is used to determine the landslide influence factor taking into account the intensity of action that is included in each slope unit according to the coordinate range of each slope unit, and to use the landslide influence factor with the largest intensity of action in each slope unit as the current landslide influence factor taking into account the intensity of action of the landslide influence factor in each slope unit; The landslide susceptibility assessment unit is used to input multiple current landslide influencing factors that take into account the intensity of the landslide influencing factors in 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 based on sample data of the relationship between the landslide influencing factors that take into account the intensity of the influencing factors in the slope unit and the landslide susceptibility assessment results.

[0007] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned landslide susceptibility assessment method taking into account the intensity of influencing factors when executing the computer program.

[0008] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned landslide susceptibility assessment method taking into account the intensity of influencing factors.

[0009] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the landslide susceptibility assessment method taking into account the intensity of influencing factors is implemented.

[0010] Compared with the technical solutions in the prior art that use the majority statistics method and the average value method to process landslide influencing factor data but fail to take into account the intensity of the effect of the influencing factors on the occurrence of landslides, thereby affecting the accuracy of landslide susceptibility assessment, the landslide susceptibility assessment solution that takes into account the intensity of the effect of the influencing factors provided in the embodiments of the present invention can take into account the intensity of the effect of the landslide influencing factors on the occurrence of landslides within the slope unit, accurately perform landslide susceptibility assessment, and improve the accuracy of landslide susceptibility assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 It is a flow chart of a landslide susceptibility assessment method taking into account the strength of influencing factors in an embodiment of the present invention; Figure 2 A grid image of B value generation provided by an embodiment of the present invention; Figure 3 A grid image generated by C value calculation provided by an embodiment of the present invention; Figure 4 A third grid image provided by an embodiment of the present invention; Figure 5 A slope unit extraction result diagram provided by an embodiment of the present invention; Figure 6 A landslide impact factor diagram taking into account the intensity of action provided by an embodiment of the present invention, Figure 6 (a) is the lithology map. Figure 6 (b) is the remote sensing ecological index map. Figure 6 Middle (c) is a soil type map; Figure 7 A landslide susceptibility assessment result diagram provided by an embodiment of the present invention; Figure 8 Schematic diagram of the structure of a landslide susceptibility assessment device taking into account the intensity of influencing factors in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0013] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of laws and regulations.

[0014] Figure 1 FIG. 4 is a flow chart of a landslide susceptibility assessment method taking into account the strength of influencing factors in an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps: Step 101: Based on the digital elevation model data of the area to be evaluated, a plurality of slope units and a coordinate range of each slope unit are determined from the area to be evaluated; Step 102: obtaining a plurality of landslide impact factors in the area to be assessed; Step 103: performing interval division processing on each landslide impact factor in the area to be assessed, and obtaining a plurality of landslide impact factors after the interval division processing; Step 104: quantifying the effect intensity of each landslide influencing factor on the occurrence of landslide after the interval division process, and obtaining each landslide influencing factor taking into account the effect intensity; Step 105: determining the landslide impact factor considering the action intensity in each slope unit according to the coordinate range of each slope unit, and taking the landslide impact factor with the largest action intensity in each slope unit as the current landslide impact factor considering the action intensity of the landslide impact factor in each slope unit; Step 106: Input multiple current landslide influencing factors that take into account the intensity of landslide influencing factors in slope units into a landslide susceptibility assessment model to obtain a landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained and generated based on sample data of the relationship between historical landslide influencing factors that take into account the intensity of influencing factors in slope units and landslide susceptibility assessment results.

[0015] The landslide susceptibility assessment method taking into account the intensity of influencing factors provided in the embodiment of the present invention, when working: obtaining digital elevation model data of the area to be assessed, determining multiple slope units from the area to be assessed, and the coordinate range of each slope unit; obtaining multiple landslide influencing factors in the area to be assessed; performing interval division processing on each landslide influencing factor in the area to be assessed, and obtaining multiple landslide influencing factors after the interval division processing; quantifying the intensity of the effect of each landslide influencing factor on the occurrence of landslide after the interval division processing, and obtaining each landslide influencing factor taking into account the intensity of the effect; according to the coordinate range, determine the landslide influence factor considering the intensity of action included in each slope unit, take the landslide influence factor with the largest intensity of action in each slope unit as the current landslide influence factor considering the intensity of action of the landslide influence factor in each slope unit; input multiple current landslide influence factors considering the intensity of action of the landslide influence factors in 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 considering the intensity of action of the influence factors in the slope units and the landslide susceptibility assessment results in history.

[0016] Compared with the technical solutions in the prior art that fail to take into account the intensity of the influencing factors on the occurrence of landslides when processing landslide influencing factor data, thereby affecting the accuracy of landslide susceptibility assessment, the landslide susceptibility assessment method taking into account the intensity of the influencing factors provided in the embodiments of the present invention can take into account the intensity of the landslide influencing factors on the occurrence of landslides within the slope unit, accurately perform landslide susceptibility assessment, and improve the accuracy of landslide susceptibility assessment. The landslide susceptibility assessment method taking into account the intensity of the influencing factors is introduced in detail below.

[0017] In the existing process of quantifying landslide influencing factors in slope units, the majority statistics method and the average value method fail to take into account the intensity of the influencing factors on the occurrence of landslides when processing landslide influencing factor data, and fail to accurately determine and extract the key factor characteristics with a large intensity of landslide action, 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 influencing factors within the slope unit, that is, in view of 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 influencing factors within the slope unit to solve the problem that the majority statistics method and the average value method fail to take into account the intensity of the influencing factors on the occurrence of landslides when processing landslide influencing factor data, and fail to accurately determine and extract the key factor characteristics with a large intensity of landslide action, which affects the accuracy and credibility of the landslide susceptibility assessment. Figures 1 to 7 The embodiments of the present invention are described in further detail.

[0018] 1. First, the steps of pre-training a landslide susceptibility assessment model are introduced.

[0019] In the step of pre-training the landslide susceptibility assessment model, historical data are used, such as historical landslide impact factor data in the study area, and multiple historical slope units determined from the study area.

[0020] In one embodiment, the above landslide susceptibility assessment method taking into account the strength of influencing factors may also include 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, multiple historical slope units and the coordinate range of each historical slope unit are determined from the study area; Obtain multiple historical landslide impact factors in the study area; 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; The intensity of each historical landslide impact factor on landslide occurrence after quantification interval division is obtained to obtain each historical landslide impact factor taking into account the intensity of the impact; According to the coordinate range of each historical slope unit, determine the historical landslide impact factor that takes into account the action intensity and is included in each historical slope unit, and take the landslide impact factor with the largest action intensity in each historical slope unit as the historical landslide impact factor that takes into account the action intensity of the landslide impact factor in each slope unit; The landslide susceptibility assessment network is trained by taking into account the historical landslide influencing factors that take into account the intensity of the landslide influencing factors in the slope unit and the corresponding historical landslide susceptibility assessment results as relationship sample data to obtain the landslide susceptibility assessment model.

[0021] In specific implementation, the above method of pre-training and generating a landslide susceptibility assessment model can improve the accuracy of quantifying the intensity of the effect of each landslide influencing factor on the occurrence of landslides, thereby improving the accuracy of landslide susceptibility assessment.

[0022] The following is a detailed introduction to the method of training the landslide susceptibility assessment model.

[0023] 1. First, we introduce the extraction of slope units based on DEM data, that is, based on the digital elevation model data of the study area, we determine multiple historical slope units from the study area, as well as the coordinate range of each historical slope unit.

[0024] The method for extracting slope units based on DEM data may include the following steps: (1) Based on the DEM data, for each raster pixel, compare the value of the current pixel with the difference between the preset number of neighboring pixels, for example, 8 pixels, and record it as A (the difference between the value of the current raster pixel and the values ​​of the preset number of raster pixels adjacent to the current raster pixel). Select the neighboring pixel with the largest A as the flow direction of the raster pixel, repeat the operation to assign a flow direction value to each pixel, record it as B (flow direction value); then generate a raster map (first raster map) based on the B value of each pixel, as shown in Figure 2 As shown, Figure 2 A grid image of B value generation provided by an embodiment of the present invention.

[0025] (2) All pixels are assigned an aggregation value, denoted as C (aggregation value). The initial value of C is 0. Figure 2 (First grid map) Reversely traverse each pixel to check its B value. If the B value of the current pixel points to a pixel in the adjacent pixel, add 1 to the C of the current pixel as the C value of the adjacent pixel being pointed to. Repeat this process to complete the C value calculation of all pixels, thereby generating a grid map (second grid map), as shown in Figure 3 As shown, Figure 3 A grid image generated by C value calculation provided in an embodiment of the present invention.

[0026] (3) Then set a threshold (preset clustering threshold) Figure 3 All pixels in the second raster image whose C value is greater than the threshold are marked as D. Figure 2 (First grid image) Link all pixels with D to generate network e. Starting from the pixel with C = 0, use Figure 2 (first grid map) and network e are linked in the direction of B value to generate grid map f (third grid map), as shown in Figure 4 As shown, Figure 4 The third grid image provided in the embodiment of the present invention uses a grid-to-polygon tool to convert f into a surface, denoted as g, to obtain a plurality of preliminary slope unit surfaces.

[0027] (4) Then, the maximum value in the DEM data is subtracted from each pixel in the DEM data to obtain the inverted DEM data, and then the inverted f surface is calculated according to the above steps and recorded as h.

[0028] (5) G and h are combined, and the unreasonable pixels that are too small, fragmented, or overly elongated, which 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, such as Figure 5 As shown, Figure 5 A slope unit extraction result diagram provided in an embodiment of the present invention.

[0029] In one embodiment, based on the digital elevation model data of the study area, a plurality of historical slope units are determined from the study area, and the coordinate range of each historical slope unit may include: Based on the digital elevation model data of the area to be evaluated, for each grid pixel in the area to be evaluated, the following operations are performed to determine the flow direction value of each grid pixel and the corresponding first grid map: compare the difference between the value of the current grid pixel and the values ​​of a preset number of grid pixels adjacent to the current grid pixel; select the adjacent grid pixel with the largest difference as the flow direction of the current grid pixel, and assign a flow direction value to the current grid pixel; generate the first grid map according to the flow direction value of each grid pixel; Based on the first grid map, for each grid pixel in the area to be evaluated, the following operations are performed to determine the clustering value of each grid pixel and the corresponding second grid map: assign an clustering value to each grid pixel, the initial value of the clustering value is 0, reversely traverse each grid pixel according to the first grid map to check the flow direction value of the current grid pixel, if the flow direction corresponding to the flow direction value of the current grid pixel points to an adjacent grid pixel among the grid pixels adjacent to the current grid pixel, add 1 to the clustering value of the current grid pixel as the clustering value of the adjacent grid pixel pointed to, until the clustering values ​​of all grid pixels are determined, and generate the second grid map according to the clustering value of each grid pixel; Assign a preset mark to all grid pixels in the second grid map whose clustering values ​​are greater than a preset clustering threshold, use the first grid map to link all grid pixels marked with the preset mark to generate a network, start from the grid pixel with a clustering 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; Subtracting the maximum value in the digital elevation model data from each grid pixel of the digital elevation model data to obtain inverted digital elevation model data, and obtaining an inverted surface according to the inverted digital elevation model data; The face and the inverted face are merged to obtain a plurality of slope units and the coordinate range of each slope unit.

[0030] In a specific implementation, the above method of determining a plurality of historical slope units from a study area can improve the extraction accuracy of slope units.

[0031] In one embodiment, merging a face and an inverted face to obtain a plurality of historical slope units may include: merging the face and the inverted face, and correcting unreasonable grid pixels that affect the integrity and continuity of the slope unit, such as an area smaller than a preset area threshold, a shape fragmentation degree exceeding a preset fragmentation threshold, or elongation exceeding a preset elongation threshold, to obtain a plurality of historical slope units.

[0032] In specific implementation, the above method of correcting unreasonable grid pixels can improve the extraction accuracy of slope units.

[0033] In one embodiment, the preset number of grid pixels may range from 6 to 10. Preferably, the preset number of grid pixels may be 8, which can improve the extraction accuracy of the slope unit.

[0034] 2. Secondly, it introduces the acquisition of environmental impact factor data related to landslides in the study area from the aspects of 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. The landslide impact factors are unified in coordinates and extracted using the vector shape elements of the area to be evaluated to obtain landslide impact factors that are consistent with the spatial coordinates and shape size of the area to be evaluated. That is, the above-mentioned acquisition of multiple historical landslide impact factors in the study area includes: 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.

[0035] 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: (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).

[0036] (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 C 1and C 2 ; Calculate the total number of landslide and non-landslide samples in each interval, denoted 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. u (The fourth quotient) is large, then it will be merged, otherwise it will not be merged. The merged new interval will become a new candidate interval, and the above steps will be repeated until the merged X value is greater than the preset threshold, and finally a group of intervals that cannot be merged will be obtained, thus completing the interval processing of the continuous landslide influencing factors.

[0037] 4. Again, the effect of quantified landslide influencing factors on landslide occurrence is introduced, that is, the effect of each type of historical landslide influencing factors on landslide occurrence after quantified interval division is obtained, and each type of historical landslide influencing factors taking into account the effect intensity are obtained. The specific methods for quantifying the effect intensity of landslide influencing factors on landslide occurrence include: Determine the number of landslide points in different intervals of a single landslide impact factor after the above intervalization is completed, denoted as N u , the area of ​​different intervals is recorded as S u , calculate N u With S u The quotient is recorded as J. Next, the number of landslide points in the entire study area is counted, recorded as N; the total area of ​​the influencing factors is recorded as S; the quotient of N and S is calculated, recorded as K. Finally, the value obtained by taking the quotient of J and K and taking the logarithm (ln) is recorded as L, which is the intensity of the influencing factors on the occurrence of landslides.

[0038] In one embodiment, the historical effect intensity of each historical landslide impact factor on the occurrence of landslide after quantifying the interval division process is obtained to obtain each historical landslide impact factor taking into account the effect intensity, which may include: 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; Determine the first quotient of the number of landslides in different intervals and the area in different intervals for each landslide influencing factor; Determine the number of landslide sites in the entire study area and the total area of ​​all influencing factors in the entire study area; 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; The quotient of the first quotient and the second quotient is obtained and the logarithm is obtained as the action intensity of each landslide influencing factor on the occurrence of landslide. Each action intensity is associated with the corresponding landslide influencing factor to obtain each landslide influencing factor taking into account the action intensity.

[0039] In specific implementation, the above quantification of the effect intensity of each landslide influencing factor on the occurrence of landslides can improve the accuracy of quantifying the effect intensity of each landslide influencing factor on the occurrence of landslides, thereby improving the accuracy of landslide susceptibility assessment.

[0040] 5. Next, the historical landslide impact factor considering the intensity of action of each historical slope unit is determined according to the coordinate range of each historical slope unit. The landslide impact factor with the largest intensity of action in each historical slope unit is used as the historical landslide impact factor considering the intensity of action of the landslide impact factor in each slope unit: The attribute value of the influencing factor with large action intensity is assigned to each corresponding slope unit, that is, each slope unit has an action intensity value, recorded as X （max,i） The same operation is then performed on all slope units and landslide influence factors, thereby generating a historical landslide influence factor that takes into account the intensity of the landslide influence factor in each slope unit. Figure 6 The influencing factor diagram of multiple types of landslides taking into account the intensity of action provided by the present invention, Figure 6 (a) is the lithology map. Figure 6 (b) is the remote sensing ecological index map. Figure 6 (c) is the soil type map, X （max,i） =max( X i1 ,X i2 ,......X im ), where m represents the mth action intensity value contained in slope unit i.

[0041] 6. Finally, it is introduced that the landslide impact factor taking into account the intensity of action is applied to the machine learning model, and the training data set is used for training to carry out landslide susceptibility assessment, that is, a landslide susceptibility assessment model for landslide susceptibility assessment is obtained by training, and multiple types of historical landslide impact factors taking into account the intensity of action of the landslide impact factor in the slope unit and the corresponding historical landslide susceptibility assessment results are used as relationship sample data to train the landslide susceptibility assessment network to obtain the landslide susceptibility assessment model. When testing or verifying the model, the landslide impact factor taking into account the intensity of action (the historical landslide impact factor taking into account the intensity of action of the landslide impact factor in the slope unit) can be used as the input of the landslide susceptibility assessment model, and 0 and 1 are used as labels. The 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 in the area. Figure 7 This is a landslide susceptibility assessment result diagram provided in an embodiment of the present invention.

[0042] Second, the steps of using the landslide susceptibility assessment model obtained by the above pre-training to conduct real-time landslide susceptibility assessment on the assessment area are introduced, namely, the above steps 101 to 106. Among them: In one embodiment, in the above step 101, based on the digital elevation model data of the area to be evaluated, a plurality of slope units and a coordinate range of each slope unit are determined from the area to be evaluated, which may include: Based on the digital elevation model data of the area to be evaluated, for each grid pixel in the area to be evaluated, the following operations are performed to determine the flow direction value of each grid pixel and the corresponding first grid map: compare the difference between the value of the current grid pixel and the values ​​of a preset number of grid pixels adjacent to the current grid pixel; select the adjacent grid pixel with the largest difference as the flow direction of the current grid pixel, and assign a flow direction value to the current grid pixel; generate the first grid map according to the flow direction value of each grid pixel; Based on the first grid map, for each grid pixel in the area to be evaluated, the following operations are performed to determine the clustering value of each grid pixel and the corresponding second grid map: assign an clustering value to each grid pixel, the initial value of the clustering value is 0, reversely traverse each grid pixel according to the first grid map to check the flow direction value of the current grid pixel, if the flow direction corresponding to the flow direction value of the current grid pixel points to an adjacent grid pixel among the grid pixels adjacent to the current grid pixel, add 1 to the clustering value of the current grid pixel as the clustering value of the adjacent grid pixel pointed to, until the clustering values ​​of all grid pixels are determined, and generate the second grid map according to the clustering value of each grid pixel; Assign a preset mark to all grid pixels in the second grid map whose clustering values ​​are greater than a preset clustering threshold, use the first grid map to link all grid pixels marked with the preset mark to generate a network, start from the grid pixel with a clustering 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; Subtracting the maximum value in the digital elevation model data from each grid pixel of the digital elevation model data to obtain inverted digital elevation model data, and obtaining an inverted surface according to the inverted digital elevation model data; The face and the inverted face are merged to obtain a plurality of slope units and the coordinate range of each slope unit.

[0043] In a specific implementation, the above method of determining a plurality of slope units from the area to be evaluated can improve the extraction accuracy of the slope units.

[0044] In one embodiment, a face and an inverted face are merged to obtain a slope unit, including: merging the face and the inverted face, and correcting unreasonable grid pixels that affect the integrity and continuity of the slope unit, such as an area smaller than a preset area threshold, a shape fragmentation degree exceeding a preset fragmentation threshold, or elongation exceeding a preset elongation threshold, to obtain multiple slope units.

[0045] In specific implementation, the above method of correcting unreasonable grid pixels can improve the extraction accuracy of slope units.

[0046] In one embodiment, the preset number of grid pixels may range from 6 to 10, preferably 8, which can improve the extraction accuracy of the slope unit.

[0047] In one embodiment, in the above step 102, the step of obtaining multiple landslide impact factors in the area to be evaluated can refer to the introduction of "2" in "1" above.

[0048] In one embodiment, in the above step 103, the intensity of each landslide impact factor after the interval division process on the occurrence of the landslide is quantified to obtain each landslide impact factor taking into account the intensity of the impact, which may include: 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; Determine the first quotient of the number of landslides in different intervals and the area in different intervals for each landslide influencing factor; Determine the number of landslide points in the entire area to be assessed, as well as the total area of ​​all influencing factors in the entire area to be assessed; Determine the second quotient of the number of landslide points in the entire area to be assessed and the total area of ​​all influencing factors in the entire area to be assessed; The quotient of the first quotient and the second quotient is obtained and the logarithm is obtained as the action intensity of each landslide influencing factor on the occurrence of landslide. Each action intensity is associated with the corresponding landslide influencing factor to obtain each landslide influencing factor taking into account the action intensity.

[0049] In specific implementation, the above quantification of the effect intensity of each landslide influencing factor on the occurrence of landslides can improve the accuracy of quantifying the effect intensity of each landslide influencing factor on the occurrence of landslides, thereby improving the accuracy of landslide susceptibility assessment.

[0050] Each step of the above-mentioned landslide susceptibility assessment for the area to be assessed can be implemented by referring to the above-mentioned step of pre-training the landslide susceptibility assessment model.

[0051] The beneficial effect of the landslide susceptibility assessment method that takes into account the intensity of influencing factors provided by the embodiment of the present invention is: the embodiment of the present invention uses drone data and remote sensing data as data sources to construct a landslide susceptibility assessment method that can take into account the intensity of influencing factors within the slope unit. The landslide influencing factors quantified by this method can fully take into account the intensity of the influencing factors on the occurrence of landslides, accurately determine and extract the characteristics of key factors with high intensity of landslide occurrence, and provide a data basis for the accurate assessment of landslide susceptibility. The landslide influencing factors that take into account the intensity of action are combined with machine learning models to assess landslide susceptibility. The results have high accuracy and can accurately and clearly assess the risk level and spatial location of landslide disasters in the study area, which has important practical significance for geological disaster early warning and disaster prevention and mitigation.

[0052] The present invention also provides a device for assessing the susceptibility of landslides taking into account the strength of influencing factors, as described in the following embodiments. Since the principle of solving the problem by the device is similar to that of the method for assessing the susceptibility of landslides taking into account the strength of influencing factors, the implementation of the device can refer to the implementation of the method for assessing the susceptibility of landslides taking into account the strength of influencing factors, and the repeated parts will not be repeated.

[0053] Figure 8 FIG. 4 is a schematic diagram of the structure of a landslide susceptibility assessment device taking into account the strength of influencing factors in an embodiment of the present invention. Figure 8 As shown, the device comprises: The extraction unit 01 is used to determine a plurality of slope units and a 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; An acquisition unit 02 is used to acquire a plurality of landslide impact factors in the area to be evaluated; An interval division processing unit 03 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 the interval division processing; The action intensity quantification unit 04 is used to quantify the action intensity of each landslide influencing factor after the interval division process on the occurrence of the landslide, and obtain each landslide influencing factor taking into account the action intensity; The unit 05 for determining the influence factor taking into account the intensity of action is used to determine the landslide influence factor taking into account the intensity of action that is included in each slope unit according to the coordinate range of each slope unit, and to use the landslide influence factor with the largest intensity of action in each slope unit as the current landslide influence factor of the intensity of action of the landslide influence factor in each slope unit; The landslide susceptibility assessment unit 06 is used to input multiple current landslide influencing factors that take into account the intensity of the landslide influencing factors in the slope unit into the landslide susceptibility assessment model to obtain a landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained and generated based on the sample data of the relationship between the landslide influencing factors that take into account the intensity of the influencing factors in the slope unit and the landslide susceptibility assessment results.

[0054] In one embodiment, the extraction unit may be specifically used for: Based on the digital elevation model data of the area to be evaluated, for each grid pixel in the area to be evaluated, the following operations are performed to determine the flow direction value of each grid pixel and the corresponding first grid map: compare the difference between the value of the current grid pixel and the values ​​of a preset number of grid pixels adjacent to the current grid pixel; select the adjacent grid pixel with the largest difference as the flow direction of the current grid pixel, and assign a flow direction value to the current grid pixel; generate the first grid map according to the flow direction value of each grid pixel; Based on the first grid map, for each grid pixel in the area to be evaluated, the following operations are performed to determine the clustering value of each grid pixel and the corresponding second grid map: assign an clustering value to each grid pixel, the initial value of the clustering value is 0, reversely traverse each grid pixel according to the first grid map to check the flow direction value of the current grid pixel, if the flow direction corresponding to the flow direction value of the current grid pixel points to an adjacent grid pixel among the grid pixels adjacent to the current grid pixel, add 1 to the clustering value of the current grid pixel as the clustering value of the adjacent grid pixel pointed to, until the clustering values ​​of all grid pixels are determined, and generate the second grid map according to the clustering value of each grid pixel; Assign a preset mark to all grid pixels in the second grid map whose clustering values ​​are greater than a preset clustering threshold, use the first grid map to link all grid pixels marked with the preset mark to generate a network, start from the grid pixel with a clustering 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; Subtracting the maximum value in the digital elevation model data from each grid pixel of the digital elevation model data to obtain inverted digital elevation model data, and obtaining an inverted surface according to the inverted digital elevation model data; The face and the inverted face are merged to obtain a plurality of slope units and the coordinate range of each slope unit.

[0055] In one embodiment, a face and an inverted face are merged to obtain a slope unit, including: merging the face and the inverted face, and correcting unreasonable grid pixels that affect the integrity and continuity of the slope unit, such as an area smaller than a preset area threshold, a shape fragmentation degree exceeding a preset fragmentation threshold, or elongation exceeding a preset elongation threshold, to obtain multiple slope units.

[0056] In one embodiment, the preset number of grid pixels may range from 6 to 10.

[0057] In one embodiment, the above-mentioned action intensity quantification unit can be specifically used for: 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; Determine the first quotient of the number of landslides in different intervals and the area in different intervals for each landslide influencing factor; Determine the number of landslide points in the entire area to be assessed, as well as the total area of ​​all influencing factors in the entire area to be assessed; Determine the second quotient of the number of landslide points in the entire area to be assessed and the total area of ​​all influencing factors in the entire area to be assessed; The quotient of the first quotient and the second quotient is obtained and the logarithm is obtained as the action intensity of each landslide influencing factor on the occurrence of landslide. Each action intensity is associated with the corresponding landslide influencing factor to obtain each landslide influencing factor taking into account the action intensity.

[0058] In one embodiment, the landslide susceptibility assessment device taking into account the strength of influencing factors provided by the embodiment of the present invention may further include a training unit for 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, multiple historical slope units and the coordinate range of each historical slope unit are determined from the study area; Obtain multiple historical landslide impact factors in the study area; 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; The intensity of each historical landslide impact factor on landslide occurrence after quantification interval division is obtained to obtain each historical landslide impact factor taking into account the intensity of the impact; According to the coordinate range of each historical slope unit, determine the historical landslide impact factor that takes into account the action intensity and is included in each historical slope unit, and take the landslide impact factor with the largest action intensity in each historical slope unit as the historical landslide impact factor that takes into account the action intensity of the landslide impact factor in each slope unit; The landslide susceptibility assessment network is trained by taking into account the historical landslide influencing factors that take into account the intensity of the landslide influencing factors in the slope unit and the corresponding historical landslide susceptibility assessment results as relationship sample data to obtain the landslide susceptibility assessment model.

[0059] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned landslide susceptibility assessment method taking into account the intensity of influencing factors when executing the computer program.

[0060] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned landslide susceptibility assessment method taking into account the intensity of influencing factors.

[0061] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the landslide susceptibility assessment method taking into account the intensity of influencing factors is implemented.

[0062] In the embodiments of the present invention, the landslide susceptibility assessment scheme that takes into account the intensity of the influencing factors can take into account the intensity of the effect of the landslide influencing factors on the occurrence of landslides within the slope unit, accurately perform landslide susceptibility assessment, and improve the accuracy of landslide susceptibility assessment, compared with the technical schemes in the prior art that fail to take into account the intensity of the effect of the influencing factors on the occurrence of landslides when processing landslide influencing factor data and thus affect the accuracy of landslide susceptibility assessment.

[0063] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0064] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0065] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0067] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A landslide susceptibility assessment method taking into account the intensity of influencing factors, characterized in that: include: Based on the digital elevation model data of the area to be evaluated, a plurality of slope units and a coordinate range of each slope unit are determined from the area to be evaluated; Obtain multiple landslide impact factors in the area to be assessed; Perform interval division processing on each landslide impact factor in the area to be assessed, and obtain multiple landslide impact factors after interval division processing; The intensity of each landslide influencing factor on the occurrence of landslide after quantification interval division is obtained to obtain each landslide influencing factor taking into account the intensity of the action; According to the coordinate range of each slope unit, determine the landslide impact factor considering the action intensity included in each slope unit, and take the landslide impact factor with the largest action intensity in each slope unit as the current landslide impact factor considering the action intensity of the landslide impact factor in each slope unit; A plurality of current landslide influencing factors taking into account the intensity of the landslide influencing factors within the slope unit are input into a landslide susceptibility assessment model to obtain a landslide susceptibility assessment result; the landslide susceptibility assessment model is pre-trained and generated based on sample data of the relationship between the landslide influencing factors taking into account the intensity of the influencing factors within the slope unit and the landslide susceptibility assessment results.

2. The method according to claim 1, characterized in that Based on the digital elevation model data of the area to be evaluated, multiple slope units and the coordinate range of each slope unit are determined from the area to be evaluated, including: Based on the digital elevation model data of the area to be evaluated, for each grid pixel in the area to be evaluated, the following operations are performed to determine the flow direction value of each grid pixel and the corresponding first grid map: compare the difference between the value of the current grid pixel and the values ​​of a preset number of grid pixels adjacent to the current grid pixel; select the adjacent grid pixel with the largest difference as the flow direction of the current grid pixel, and assign a flow direction value to the current grid pixel; generate the first grid map according to the flow direction value of each grid pixel; Based on the first grid map, for each grid pixel in the area to be evaluated, the following operations are performed to determine the clustering value of each grid pixel and the corresponding second grid map: assign an clustering value to each grid pixel, the initial value of the clustering value is 0, reversely traverse each grid pixel according to the first grid map to check the flow direction value of the current grid pixel, if the flow direction corresponding to the flow direction value of the current grid pixel points to an adjacent grid pixel among the grid pixels adjacent to the current grid pixel, add 1 to the clustering value of the current grid pixel as the clustering value of the adjacent grid pixel pointed to, until the clustering values ​​of all grid pixels are determined, and generate the second grid map according to the clustering value of each grid pixel; Assign a preset mark to all grid pixels in the second grid map whose clustering values ​​are greater than a preset clustering threshold, use the first grid map to link all grid pixels marked with the preset mark to generate a network, start from the grid pixel with a clustering 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; Subtracting the maximum value in the digital elevation model data from each grid pixel of the digital elevation model data to obtain inverted digital elevation model data, and obtaining an inverted surface according to the inverted digital elevation model data; The face and the inverted face are merged to obtain a plurality of slope units and the coordinate range of each slope unit.

3. The method according to claim 2, characterized in that The face and the inverted face are merged to obtain a plurality of slope units, including: merging the face and the inverted face, and correcting unreasonable grid pixels that affect the integrity and continuity of the slope unit, such as an area smaller than a preset area threshold, a shape fragmentation degree exceeding a preset fragmentation threshold, or elongation exceeding a preset elongation threshold, to obtain a plurality of slope units.

4. The method according to claim 2, characterized in that The preset number of grid pixels ranges from 6 to 10.

5. The method according to claim 1, characterized in that The intensity of each landslide influencing factor on the occurrence of landslide after quantification interval division is obtained, and each landslide influencing factor taking into account the intensity of action is obtained, including: 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; Determine the first quotient of the number of landslides in different intervals and the area in different intervals for each landslide influencing factor; Determine the number of landslide points in the entire area to be assessed, as well as the total area of ​​all influencing factors in the entire area to be assessed; Determine the second quotient of the number of landslide points in the entire area to be assessed and the total area of ​​all influencing factors in the entire area to be assessed; The quotient of the first quotient and the second quotient is obtained and the logarithm is obtained as the action intensity of each landslide influencing factor on the occurrence of landslide. Each action intensity is associated with the corresponding landslide influencing factor to obtain each landslide influencing factor taking into account the action intensity.

6. The method according to claim 1, characterized in that 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, multiple historical slope units and the coordinate range of each historical slope unit are determined from the study area; Obtain multiple historical landslide impact factors in the study area; 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; The intensity of each historical landslide impact factor on landslide occurrence after quantification interval division is obtained to obtain each historical landslide impact factor taking into account the intensity of the impact; According to the coordinate range of each historical slope unit, determine the historical landslide impact factor that takes into account the action intensity and is included in each historical slope unit, and take the landslide impact factor with the largest action intensity in each historical slope unit as the historical landslide impact factor that takes into account the action intensity of the landslide impact factor in each slope unit; The landslide susceptibility assessment network is trained by taking into account the historical landslide influencing factors that take into account the intensity of the landslide influencing factors in the slope unit and the corresponding historical landslide susceptibility assessment results as relationship sample data to obtain the landslide susceptibility assessment model.

7. A landslide susceptibility assessment device taking into account the intensity of influencing factors, characterized in that: include: An extraction unit is used to determine a plurality of slope units and a 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; An acquisition unit, used for acquiring a plurality of landslide impact factors in the area to be assessed; An interval division processing unit is used to perform interval division processing on each landslide impact factor in the area to be assessed, and obtain multiple landslide impact factors after the interval division processing; The action intensity quantification unit is used to quantify the action intensity of each landslide influencing factor on the occurrence of landslide after the interval division process, and obtain each landslide influencing factor taking into account the action intensity; The unit for determining the influence factor taking into account the intensity of action is used to determine the landslide influence factor taking into account the intensity of action that is included in each slope unit according to the coordinate range of each slope unit, and to use the landslide influence factor with the largest intensity of action in each slope unit as the current landslide influence factor taking into account the intensity of action of the landslide influence factor in each slope unit; The landslide susceptibility assessment unit is used to input multiple current landslide influencing factors that take into account the intensity of the landslide influencing factors in 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 based on sample data of the relationship between the landslide influencing factors that take into account the intensity of the influencing factors in the slope unit and the landslide susceptibility assessment results.

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, the method according to any one of claims 1 to 6 is implemented.

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, the method according to any one of claims 1 to 6 is implemented.

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

Images