Slope stability prediction method and device under rainfall conditions

Abstract

The application provides a slope stability prediction method and device under rainfall conditions, and relates to the technical field of slope stability prediction. The method comprises the following steps: dividing the slope by using a regular grid and constructing a time-space feature data set containing geological, hydrological and topographic parameters; calculating a regional coordination index based on a multi-dimensional feature vector, dividing the slope into multiple communities and isolated risk areas; calculating the dynamic safety factor of each community with the centroid sub-region as the representative, and dividing the stability level according to the threshold value; establishing a three-dimensional digital twin model to realize risk visualization, triggering an early warning for the area with a continuously decreasing safety factor in three periods and showing the evolution track. The method realizes accurate monitoring and early warning of slope stability through multi-source data fusion and dynamic partition evaluation.

Description

Technical Field

[0001] This invention relates to the field of slope stability prediction technology, specifically to a method and apparatus for predicting slope stability under rainfall conditions. Background Technology

[0002] In slope stability analysis, traditional methods typically rely on static data, such as soil physical and mechanical properties, slope, and vegetation cover. These methods often employ empirical formulas and simple limit equilibrium analyses, failing to encompass potential risks arising from dynamic changes. For example, the intensity and duration of rainfall significantly affect soil moisture content and pore water pressure, leading to variations in soil strength. However, current technologies often fail to monitor rainfall and its impact on slope stability in real time. Therefore, static assessments often cannot accurately reflect the actual slope safety status, especially under extreme weather conditions, leading to an increased incidence of landslides and posing a serious threat to personnel and property safety.

[0003] Furthermore, traditional slope stability assessments lack a comprehensive consideration of spatiotemporal dynamics, often relying on isolated analyses based on local features, making it difficult to effectively identify and delineate potential risk zones. In many cases, complex interactions exist between different sub-regions of a slope, relationships often overlooked in traditional methods. Existing technologies, in acquiring and processing slope characteristic data, cannot timely integrate information from different sources, such as real-time rainfall intensity, geological parameters, and hydrological conditions, affecting real-time assessments of the overall slope safety and stability. Moreover, the lack of effective intelligent monitoring methods limits the response speed and accuracy of slope risk assessments, hindering the formation of an efficient early warning mechanism. Therefore, there is an urgent need for a dynamic monitoring and assessment method integrating multidimensional data to address complex and changing natural environmental conditions, thereby improving the scientific rigor and effectiveness of slope management.

[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide a method and apparatus for predicting slope stability under rainfall conditions, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A method for predicting slope stability under rainfall conditions, comprising the following steps:

[0008] Step 1: Discretize the target slope into several sub-regions using a regular grid, assign regional attributes including geological parameters, hydrological parameters, and topographic parameters to each sub-region, and integrate real-time rainfall intensity data provided by meteorological radar to form a slope feature dataset with spatiotemporal attributes.

[0009] Step 2: Based on the geological, hydrological and topographic parameters of each sub-region, use multidimensional feature vectors to characterize the local slope information of each sub-region, define the regional synergy index between any two sub-regions based on the multidimensional feature vectors, and combine the spectral clustering algorithm to cluster the sub-regions, thereby dividing the target slope into multiple communities and isolated risk areas.

[0010] Step 3: Determine the dynamic safety factor for each community and isolated risk area based on the slope feature dataset, compare the dynamic safety factor with the stability threshold, and classify the stability level of each community and isolated risk area according to the comparison results; for each community, select its centroid sub-region as a representative to determine the dynamic safety factor of the community.

[0011] Step 4: Establish a three-dimensional digital twin model of the target slope. Use a spatial mapping algorithm to accurately match the community division results with the model. In the visualization interface, use different colors to identify the stability level of each community and isolated risk area. For communities or isolated risk areas where the dynamic safety factor shows a monotonically decreasing trend over three consecutive monitoring periods, trigger a risk warning signal. At the same time, highlight the evolution trajectory of the area in the three-dimensional digital twin model.

[0012] Furthermore, a regular grid is used to discretize the target slope into several sub-regions, where the grid size is determined based on the slope scale and monitoring accuracy requirements. to The adjustable range assigns regional attributes to each sub-region, including geological parameters, hydrological parameters, and topographic parameters; the geological parameters include permeability coefficient, internal friction angle, and cohesion; the hydrological parameters include initial water content, saturated water content, and real-time pore water pressure; and the topographic parameters include slope and surface curvature.

[0013] By integrating real-time rainfall intensity data provided by meteorological radar and matching its spatiotemporal resolution with the grid division scale, a slope feature dataset with multidimensional features of time, space and attributes is finally formed, in which each parameter is stored in matrix form and a spatiotemporal index relationship is established.

[0014] Geological, hydrological, and topographic parameters were obtained through field surveys, sensor monitoring, and remote sensing measurements, serving as regional attributes for each sub-region.

[0015] Furthermore, based on the geological, hydrological, and topographic parameters of each sub-region, a multidimensional feature vector is constructed for each sub-region. The expression for the multidimensional feature vector is as follows:

[0016]

[0017] In the formula, sub-region The multidimensional feature vectors, For the index of the sub-region, , and Representing sub-regions Geological parameters, hydrological parameters, and topographic parameters, , and Sub-regions in sequence The permeability coefficient, internal friction angle, and cohesion, , and Sub-regions in sequence The initial water content, saturated water content, and real-time pore water pressure, and Sub-regions in sequence The slope and surface curvature;

[0018] The regional synergy index between any two sub-regions is defined based on multidimensional feature vectors, and the formula used is as follows:

[0019]

[0020] In the formula, Subregion and subregions Regional synergy index and The index is for the sub-region, and ; , and Representing sub-regions and subregions Differences in geological features, hydrological features, and topographic features between them; , and Representing sub-regions Geological parameters, hydrological parameters, and topographic parameters, , and Sub-regions in sequence The permeability coefficient, internal friction angle, and cohesion, , and Sub-regions in sequence The initial water content, saturated water content, and real-time pore water pressure, and Sub-regions in sequence The slope and surface curvature, , and For the preset weights, And satisfy .

[0021] Furthermore, the sub-regions are clustered using a spectral clustering algorithm, based on the following specific logic:

[0022] A regional synergy index matrix is ​​constructed based on the regional synergy index among all sub-regions. A spectral clustering algorithm is then used to divide the sub-regions into communities. Specifically, the Laplace matrix of the regional synergy index matrix is ​​calculated, and the optimal number of communities is determined through eigenvalue decomposition. The K-means algorithm was used to divide the subregion into Individual communities; setting dynamic similarity thresholds. This results in the average regional synergy index among sub-regions within the community being less than [a certain value]. The average regional synergy index among sub-regions of the community is greater than For any sub-region, if its regional synergy index with all other sub-regions is greater than or equal to the dynamic similarity threshold... If so, it is determined to be an isolated risk area;

[0023] Repeat the above similarity judgment until the community affiliation of all sub-regions no longer changes, thus forming the final community division result.

[0024] Furthermore, the dynamic safety factor for each community and isolated risk zone is determined based on the slope feature dataset, using the following formula:

[0025]

[0026] In the formula, Indicates subregion in The dynamic safety factor at any given time is used to reflect the immediate stability state of the slope under rainfall conditions; The cohesion of the soil in the sub-region, is the unit weight of the soil in the sub-region, used to characterize the normal stress component generated by the self-weight of the sliding body. The sliding body refers to the part of the soil in the sub-region that can slide along the potential sliding surface. For the potential sliding surface depth, For the sub-region slope angle, Let be the pore water pressure in the subregion at time t. The surface curvature of the sub-region Let be the radius of curvature of the slope in the sub-region. The internal friction angle of the soil in the sub-region. The permeability coefficient is related to the water content. The saturated permeability coefficient is used to characterize the maximum permeability of soil when it is fully saturated, and is determined by indoor permeability tests. The current soil moisture content of the sub-region. Residual volumetric water content represents the percentage of water in the soil that cannot be drained by gravity, and is determined by the soil type. and These are the initial moisture content and the saturated moisture content, respectively. It is an empirical index used to control the rate at which the permeability coefficient changes with water content, and is related to the soil pore distribution;

[0027] For each community, its centroid sub-region is selected as a representative to determine the community's dynamic safety coefficient. The method for selecting the centroid sub-region is as follows: First, calculate the average coordinates of the geometric centers of all sub-regions within the community as the centroid position. Then, select the sub-region with the closest Euclidean distance to this centroid position as the centroid sub-region. If multiple centroid sub-regions exist, further compare the cosine similarity between their multidimensional feature vectors and the community's average features. Select the sub-region with the highest similarity as the centroid sub-region, which must satisfy the following condition:

[0028] (1) Located within the community and not adjacent to isolated risk areas;

[0029] (2) The deviations of its geological and hydrological parameters from the community average shall not exceed .

[0030] Furthermore, the dynamic safety factor is compared with the stability threshold. Based on the comparison results, the stability level of each community and isolated risk area is classified. The specific logic behind this is as follows:

[0031] when When the community or isolated risk area is marked as stable, it means that the slope resistance force at the community or isolated risk area is significantly greater than the sliding force.

[0032] when When this occurs, the community or isolated risk area will be marked as an alert, indicating that enhanced monitoring and restrictions on entry will be necessary.

[0033] when When this occurs, the community or isolated risk area is marked as high-risk, indicating that localized landslides may occur and an emergency response plan needs to be activated.

[0034] when When this occurs, the community or isolated risk area is marked as unstable, indicating that a landslide has occurred or is imminent, and an evacuation alert is immediately triggered;

[0035] In the formula, express Dynamic safety factor at any given time. This is the preset stability threshold.

[0036] Furthermore, a three-dimensional digital twin model of the target slope is constructed based on the BIM platform, and the community division results are accurately matched with the model grid through spatial coordinate mapping. In the visualization interface, a four-color gradient rendering scheme is used to display the stability level of each community and isolated risk area in real time, and the real-time rainfall intensity distribution is overlaid. Among them, green, yellow, orange, and red represent stable state, warning state, high-risk state, and unstable state, respectively.

[0037] For areas where the dynamic safety factor decreases monotonically over three consecutive monitoring periods, an audible and visual early warning signal is automatically triggered. At the same time, the area is marked in the model with a pulse flashing effect, and an early warning report containing location coordinates, the rate of change of the dynamic safety factor, and the potential slip direction is generated. The system synchronously records the stability evolution trajectory of each area and supports displaying the landslide development process in a timeline playback manner.

[0038] The present invention also provides a slope stability prediction device under rainfall conditions, which is used to perform the above-described slope stability prediction method under rainfall conditions, including:

[0039] The slope gridding modeling module is used to discretize the target slope into several sub-regions using a regular grid, assign regional attributes to each sub-region including geological parameters, hydrological parameters and topographic parameters, and integrate real-time rainfall intensity data provided by meteorological radar to form a slope feature dataset with spatiotemporal attributes.

[0040] The intelligent community division module is used to characterize the local slope information of each sub-region using multi-dimensional feature vectors based on the geological, hydrological and topographic parameters of each sub-region. Based on the multi-dimensional feature vectors, it defines the regional coordination index between any two sub-regions and combines the spectral clustering algorithm to perform clustering processing on the sub-regions, thereby dividing the target slope into multiple communities and isolated risk areas.

[0041] The dynamic safety assessment module is used to determine the dynamic safety factor of each community and isolated risk area based on the slope feature dataset, compare the dynamic safety factor with the stability threshold, and classify the stability level of each community and isolated risk area according to the comparison results; wherein, for each community, its centroid sub-region is selected as a representative to determine the dynamic safety factor of the community.

[0042] The 3D early warning visualization module is used to establish a 3D digital twin model of the target slope. It accurately matches the community division results with the model through a spatial mapping algorithm. In the visualization interface, the stability level of each community and isolated risk area is marked with different colors. For communities or isolated risk areas where the dynamic safety factor shows a monotonically decreasing trend over three consecutive monitoring periods, a risk warning signal is triggered. At the same time, the evolution trajectory of the area is highlighted in the 3D digital twin model.

[0043] Compared with the prior art, the beneficial effects of the present invention are:

[0044] This solution discretizes slopes using a regular grid, fusing geological, hydrological, topographical, and real-time rainfall intensity data to form a slope feature dataset with spatiotemporal attributes. This enables dynamic monitoring and real-time assessment of slope conditions. Based on the calculation of a regional synergistic index using multi-dimensional feature vectors, combined with precise assessment of dynamic safety factors, potential risk zones of slopes can be effectively identified, allowing for timely implementation of corresponding early warning measures. Furthermore, the application of a three-dimensional digital twin model not only enables visual monitoring but also dynamically records the evolution trajectory of slope stability, providing decision-makers with a scientific basis and significantly improving the intelligence level and emergency response capabilities of slope management. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the overall method flow of the present invention;

[0046] Figure 2 This is a schematic diagram of the overall device module of the present invention;

[0047] Figure 3-5 The graphs show the functional relationships between cohesion, internal friction angle, pore water pressure, and dynamic safety factor. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0049] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0050] Example:

[0051] Please see Figure 1 The present invention provides a technical solution:

[0052] A method for predicting slope stability under rainfall conditions, comprising the following steps:

[0053] Step 1: Discretize the target slope into several sub-regions using a regular grid, assign regional attributes including geological parameters, hydrological parameters, and topographic parameters to each sub-region, and integrate real-time rainfall intensity data provided by meteorological radar to form a slope feature dataset with spatiotemporal attributes.

[0054] In this embodiment, a regular grid is used to discretize the target slope into several sub-regions, where the grid size is determined according to the slope scale and monitoring accuracy requirements. to The adjustable range assigns regional attributes to each sub-region, including geological parameters, hydrological parameters, and topographic parameters; the geological parameters include permeability coefficient, internal friction angle, and cohesion; the hydrological parameters include initial water content, saturated water content, and real-time pore water pressure; and the topographic parameters include slope and surface curvature.

[0055] By integrating real-time rainfall intensity data provided by meteorological radar and matching its spatiotemporal resolution with the grid division scale, a slope feature dataset with multidimensional features of time, space and attributes is finally formed, in which each parameter is stored in matrix form and a spatiotemporal index relationship is established.

[0056] Geological, hydrological, and topographic parameters were obtained through field surveys, sensor monitoring, and remote sensing measurements, serving as regional attributes for each sub-region.

[0057] Step 1 discretizes the target slope into multiple sub-regions using a regular grid, assigning detailed geological, hydrological, and topographic parameters to each sub-region. Simultaneously, real-time rainfall intensity data is integrated to form a slope feature dataset with spatiotemporal attributes. The advantage of this method lies in its systematic integration of multiple influencing factors, ensuring comprehensive monitoring and assessment of slope conditions. Compared to existing technologies, this overcomes the limitations of traditional methods in static analysis, enabling timely capture and processing of real-time dynamic changes, thereby improving the accuracy and timeliness of risk identification.

[0058] By implementing step 1, the overall scheme establishes a dynamic and comprehensive slope monitoring system, promoting the scientific rigor and accuracy of slope stability prediction. Compared to the previous approach of analyzing local features in isolation, this scheme divides the slope into multiple sub-regions, clarifying the interrelationships between different regions and thus more effectively identifying potential risk areas. This method not only improves the intelligence level of data processing but also provides a solid foundation for subsequent dynamic safety factor calculation and risk early warning, thereby further enhancing the overall efficiency and safety of slope management.

[0059] Step 2: Based on the geological, hydrological and topographic parameters of each sub-region, use multidimensional feature vectors to characterize the local slope information of each sub-region, define the regional synergy index between any two sub-regions based on the multidimensional feature vectors, and combine the spectral clustering algorithm to cluster the sub-regions. The rest are marked as isolated risk areas, thereby dividing the target slope into multiple communities and isolated risk areas.

[0060] In this embodiment, a multidimensional feature vector is constructed for each sub-region based on its geological, hydrological, and topographic parameters. The expression for the multidimensional feature vector is as follows:

[0061]

[0062] In the formula, sub-region The multidimensional feature vectors, For the index of the sub-region, , and Representing sub-regions Geological parameters, hydrological parameters, and topographic parameters, , and Sub-regions in sequence The permeability coefficient, internal friction angle, and cohesion, , and Sub-regions in sequence The initial water content, saturated water content, and real-time pore water pressure, and Sub-regions in sequence The slope and surface curvature;

[0063] The regional synergy index between any two sub-regions is defined based on multidimensional feature vectors, and the formula used is as follows:

[0064]

[0065] In the formula, Subregion and subregions Regional synergy index and The index is for the sub-region, and ; , and Representing sub-regions and subregions Differences in geological features, hydrological features, and topographic features between them; , and Representing sub-regions Geological parameters, hydrological parameters, and topographic parameters, , and Sub-regions in sequence The permeability coefficient, internal friction angle, and cohesion, , and Sub-regions in sequence The initial water content, saturated water content, and real-time pore water pressure, and Sub-regions in sequence The slope and surface curvature, , and For the preset weights, , , The weighting reflects the importance of different features in contributing to the regional synergy index. In slope stability analysis, geological features directly affect the physical properties and anti-slide capacity of the soil; therefore, their differences have the greatest impact on regional stability and are thus assigned the highest weight. Hydrological features are equally important, but their impact is relatively minor, and therefore they are assigned a medium weight. Topographic features can affect landslide risk in some cases, but compared to geological and hydrological features, their impact is usually smaller, and therefore they are assigned the lowest weight. This weighting helps to more accurately reflect the relative contributions of different features to regional synergy.

[0066] In the first given formula, the dependent variable, the regional synergy index, specifically reflects the similarity or synergy between any two sub-regions. A smaller regional synergy index value indicates greater similarity in the characteristics of the two sub-regions, meaning they are closer in terms of geological, hydrological, and topographic parameters, and vice versa. The regional synergy index helps identify regions with similar characteristics, enabling effective community delineation in slope stability prediction, thereby improving the ability to identify potential risks and management efficiency. The independent variables include geological feature differences, hydrological feature differences, and topographic feature differences, representing the differences between two sub-regions in geological, hydrological, and topographic parameters, respectively. The relationship between the independent and dependent variables is that these differences reflect the degree of similarity between the sub-regions. Specifically: geological feature differences reflect changes in geological parameters such as permeability coefficient, internal friction angle, and cohesion. These parameters directly affect the physical properties and stability of the soil, therefore their differences have a significant impact on slope stability. Hydrological feature differences reflect changes in hydrological parameters such as initial moisture content, saturated moisture content, and real-time pore water pressure. These parameters relate to the moisture state of the soil, thus affecting the slope's resistance to sliding. Topographic feature variability reflects changes in slope and surface curvature, factors that influence the potential sliding surface and stress state of landslides. Therefore, differences in topographic features directly affect slope stability. In this formula, the dependent and independent variables are positively correlated. Specifically, an increase in the value of any of the independent variables—geological feature variability, hydrological feature variability, or topographic feature variability—means that the sub-region... and subregions Increased differences between regions mean their characteristics are no longer similar. This will lead to an increase in the regional synergy index, reflecting a weakening of the synergy between the two regions. When the values ​​of geological feature difference, hydrological feature difference, or topographic feature difference decrease, it means that the characteristics between sub-regions are more similar, and the value of the regional synergy index decreases, reflecting an increase in the similarity between sub-regions.

[0067] Formulas 2, 3, and 4 calculate the differences in geological, hydrological, and topographic features between sub-regions, respectively. The rationality of these formulas lies in their use of Euclidean distance, which allows for the quantification and comprehensive consideration of differences between various features. The square root of the sum of squared differences effectively reflects the relative differences in characteristic parameters between two sub-regions. Furthermore, the introduced weights ensure that each difference has varying degrees of influence in the overall regional synergy index. This weighting method allows the model to adapt to the impact of different features on regional synergy, enhancing the flexibility and accuracy of the regional synergy index. Therefore, these formulas are not only mathematically sound but also effectively support the assessment of feature similarity in slope stability prediction.

[0068] The specific logic behind using spectral clustering algorithms to cluster sub-regions is as follows:

[0069] A regional synergy index matrix is ​​constructed based on the regional synergy index among all sub-regions. A spectral clustering algorithm is then used to divide the sub-regions into communities. Specifically, the Laplace matrix of the regional synergy index matrix is ​​calculated, and the optimal number of communities is determined through eigenvalue decomposition. The K-means algorithm was used to divide the subregion into Individual communities; setting dynamic similarity thresholds. This results in the average regional synergy index among sub-regions within the community being less than [a certain value]. The average regional synergy index among sub-regions of the community is greater than For any sub-region, if its regional synergy index with all other sub-regions is greater than or equal to the dynamic similarity threshold... If so, it is determined to be an isolated risk area;

[0070] Among them, the optimal number of communities is determined by eigenvalue decomposition. The K-means algorithm was used to divide the subregion into Each community, specifically: constructs a symmetric SCI matrix based on the regional synergy index among all sub-regions, with matrix elements... Reflecting sub-regions The geological, hydrological, and topographical similarity with sub-region j is calculated. Next, the normalized Laplacian matrix of this matrix is ​​calculated, and the eigenvectors corresponding to the top K largest eigenvalues ​​are extracted through eigenvalue decomposition. The value of K is automatically determined using the eigenvalue gap method, representing the optimal number of communities. Then, the eigenvectors are arranged into a new matrix by rows, and the K-means clustering algorithm is used to divide the row vectors into sub-regions, forming K initial communities. During this process, a similarity threshold τ is dynamically set, requiring that the average similarity within each community be satisfied. And the average between communities The threshold τ is determined through optimization based on the principle of maximizing the silhouette coefficient, under the dual conditions. For each sub-region, if its SCI (Sequence Index) with all adjacent sub-regions is ≥τ, it is identified as an isolated risk area. The community division and τ value are iteratively adjusted until the affiliation of all sub-regions no longer changes, ultimately outputting stable community division results and isolated risk area markers. This process uses a spectral clustering algorithm to transform multidimensional feature similarity into spatial clustering relationships, ensuring both the homogeneity of similar regions and the identification of isolated risk units with geological anomalies or hydrological abrupt changes.

[0071] Step 2 effectively characterizes the local information of the slope by constructing multidimensional feature vectors for each sub-region and defining a regional synergy index based on these vectors. The advantage of this method lies in its ability to comprehensively consider the relationships between geological, hydrological, and topographic parameters of different sub-regions, thereby revealing the mutual influences between regions. By applying the regional synergy index to community delineation, areas with similar characteristics can be identified more accurately, ensuring that the identification of risk areas is more accurate and scientific.

[0072] Compared to existing technologies, the implementation of step 2 significantly enhances the complexity and accuracy of slope stability prediction. Traditional methods often employ single features or static data for analysis, failing to fully consider interrelated multidimensional factors. Step 2, by introducing a regional synergy index, can dynamically assess the similarity between different sub-regions and their potential risk correlations. This design quantifies the interdependencies under different geological and hydrological conditions, thus promoting information integration and scientific decision-making within the overall scheme. Ultimately, this will provide a more reliable data foundation for subsequent steps of dynamic safety factor calculation and risk early warning, improving the overall effectiveness of slope management.

[0073] Step 3: Determine the dynamic safety factor for each community and isolated risk area based on the slope feature dataset, compare the dynamic safety factor with the stability threshold, and classify the stability level of each community and isolated risk area according to the comparison results; for each community, select its centroid sub-region as a representative to determine the dynamic safety factor of the community.

[0074] In this embodiment, the dynamic safety factor for each community and isolated risk zone is determined based on the slope feature dataset, using the following formula:

[0075]

[0076] In the formula, Indicates subregion in The dynamic safety factor at any given time is used to reflect the immediate stability state of the slope under rainfall conditions; The cohesion of the soil in the sub-region reflects the shear strength generated by the chemical bonding between soil particles, and is determined by indoor direct shear test or triaxial test. This represents the unit weight of the soil in the subregion, used to characterize the normal stress component generated by the self-weight of the sliding body. The sliding body refers to the portion of soil in the subregion that can slide along the potential sliding surface. The potential sliding surface depth determines the volume of the sliding body and its self-weight load. For the sub-region slope angle, The pore water pressure in the subregion at time t is solved by coupling the Richards equation with the real-time rainfall intensity. The surface curvature of the sub-region The ratio of the radii of curvature of the slope in the sub-region to the radius of curvature of the slope is... Used to correct local pore water pressure distribution. It is the internal friction angle of the soil in the sub-region, used to reflect the friction between soil particles. The permeability coefficient is related to the water content. The saturated permeability coefficient is used to characterize the maximum permeability of soil when it is fully saturated, and is determined by indoor permeability tests. The current soil moisture content of the sub-region. Residual volumetric water content represents the percentage of water in the soil that cannot be drained by gravity, and is determined by the soil type. and These are the initial moisture content and the saturated moisture content, respectively. This is an empirical index used to control the rate of change of permeability coefficient with water content; it is related to the soil pore distribution, and n=2. Specifically, It reflects the soil's permeability under different moisture content conditions; the higher the value, the stronger the soil's permeability. The component of the item's own weight sliding down the slope. The term represents the rate of change of pore water pressure over time, characterizing the transient seepage force caused by rainfall infiltration.

[0077] The dynamic safety coefficient of an isolated risk zone is the same as the dynamic safety coefficient of the sub-region corresponding to the isolated risk zone, and the dynamic safety coefficient of a community is the same as the dynamic safety coefficient of its centroid sub-region.

[0078] In the given first formula, the dependent variable The dynamic safety factor directly characterizes the real-time stability of a slope under rainfall conditions. Its physical meaning is the real-time ratio of the anti-sliding force to the sliding force. The larger the value, the more stable the slope and the stronger its anti-sliding ability; conversely, the smaller the value, the more unstable the slope may be and therefore has the risk of landslide. The dynamic safety factor provides a quantitative assessment of slope stability and helps to monitor and warn of potential landslide risks in real time. By coupling dynamic changes in pore water pressure With time-varying characteristics of permeability coefficient This solves the problem that traditional safety factors cannot reflect the transient effects of rainfall infiltration. The technical effects are reflected in: (1) capturing the impact of the sudden increase in pore water pressure caused by short-term heavy rainfall on stability; (2) through curvature correction terms. This study quantifies the local amplification or attenuation effect of topographic contours on water pressure distribution, improving the accuracy of shallow landslide early warning. Independent variables include cohesion, soil unit weight, potential sliding surface depth, slope angle, pore water pressure, surface curvature, slope radius of curvature, internal friction angle, and permeability coefficient related to water content. These independent variables are... The relationships are as follows: cohesion, soil unit weight, and slope angle jointly determine the normal stress component generated by the self-weight of the sliding mass and the anti-sliding force, thus affecting... The sliding force is influenced by both pore water pressure and the internal friction angle of the soil. Increased pore water pressure reduces the effective stress of the slope, thus decreasing its resistance to sliding and leading to... Decrease. Permeability coefficient related to water content. It directly affects the soil's moisture state and its resistance to sliding. When the soil's moisture content changes, the change in the permeability coefficient affects the pore water pressure, thus indirectly affecting... The ratio of the surface curvature to the radius of curvature of the slope. It also affects the sliding force; when its ratio increases, It will decrease.

[0079] Table 1: Statistical Table of Dynamic Safety Factors

[0080]

[0081] Please see Figures 3-5 In this data analysis, the soil unit weight is taken as 18. The sliding surface depth is 5m, the radius of curvature R=100m, and the pore water pressure change rate is... Overall, the dynamic safety factor shows a clear negative correlation with the slope angle. When the slope angle increases from 12° to 42°, FS(t) correspondingly decreases from 2.78 to 0.53, a drop of 81%. This trend perfectly aligns with the basic mechanical principles of slope stability: as the slope angle increases, the sliding force component increases significantly, while the anti-sliding force component decreases relatively, leading to a reduction in overall stability. Particularly noteworthy is that when the slope angle exceeds 30°, FS(t) generally drops below 1.3, entering a stability range requiring early warning. This finding provides an important reference for determining the critical slope angle in engineering practice.

[0082] Secondly, cohesion and internal friction angle, as key parameters of soil strength, have a significant impact on the dynamic safety factor. Data shows that under similar slope angle conditions (e.g., in the 20-26° range), for every 5 kPa increase in cohesion, the dynamic safety factor increases by an average of 0.25-0.35; for every 5° increase in internal friction angle, the dynamic safety factor increases by an average of 0.15-0.2. For example, comparing data from group 4 and group 5, under similar slope angles, the dynamic safety factor increased from 1.67 to 1.88, fully demonstrating that improving soil strength parameters can effectively enhance slope stability.

[0083] The influence of hydrogeological parameters is also significant. Pore water pressure shows a significant negative correlation with the dynamic safety factor; when pore water pressure increases from 3 kPa to 45 kPa, the dynamic safety factor decreases by 81%. The effect of permeability coefficient exhibits a dual nature: on the one hand, low permeability exacerbates the accumulation of pore water pressure, as seen in the dynamic safety factor of only 0.65 in group 10; on the other hand, high permeability promotes drainage, as seen in group 1, where even with a pore water pressure of 3 kPa, the dynamic safety factor remains highly stable at 2.78. The influence of surface curvature is as follows: convex slopes (i.e., surface curvature greater than zero) reduce the dynamic safety factor by an average of 12-18%, while concave slopes (i.e., surface curvature less than zero) can increase the dynamic safety factor by approximately 8-15%.

[0084] It is particularly important to note that the interaction between parameters has a significant impact on the dynamic safety factor. On steep slopes (when the slope toe > 35°), the impact of changes in hydrological parameters on the dynamic safety factor is amplified. For example, in groups 13-15, the decrease in the dynamic safety factor due to a 5 kPa increase in pore water pressure (approximately 0.08-0.1) is significantly greater than the decrease under gentle slope conditions (approximately 0.03-0.05). This phenomenon indicates that in steep slope areas, changes in water pressure caused by rainfall infiltration pose a more severe threat to stability.

[0085] Finally, critical state analysis revealed that when FS(t) < 1.0, the corresponding parameter combinations all satisfy the following characteristics: slope angle > 35°, cohesion < 10 kPa, and u(t) > 25 kPa. This result provides a clear parameter threshold reference for determining the dangerous state of slopes. The significant difference between the maximum value of FS(t) (Group 1) and the minimum value of 0.53 (Group 15) in all data fully demonstrates the necessity of considering the coupling effects of multiple parameters.

[0086] For each community, its centroid sub-region is selected as a representative to determine the community's dynamic safety coefficient. The method for selecting the centroid sub-region is as follows: First, calculate the average coordinates of the geometric centers of all sub-regions within the community as the centroid position. Then, select the sub-region with the closest Euclidean distance to this centroid position as the centroid sub-region. If multiple centroid sub-regions exist, further compare the cosine similarity between their multidimensional feature vectors and the community's average features. Select the sub-region with the highest similarity as the centroid sub-region, which must satisfy the following condition:

[0087] (1) Located within the community and not adjacent to isolated risk areas;

[0088] (2) The deviations of its geological and hydrological parameters from the community average shall not exceed .

[0089] Selecting a centroid sub-region as a representative is of significant scientific and practical importance in determining the dynamic safety factor for each community. First, by calculating the average coordinates of the geometric centers of all sub-regions within the community, the central location of the community can be accurately reflected, providing a basis for subsequent selection. Choosing the sub-region with the closest Euclidean distance to this centroid location ensures that the selected area is spatially closest to the community's core, reflecting the overall characteristics of the region. If multiple equidistant sub-regions exist, further comparison of the cosine similarity between their multidimensional feature vectors and the community's average features effectively assesses the consistency of geological and hydrological characteristics among the sub-regions, ensuring that the selected centroid sub-region better represents the overall characteristics of the community. Finally, to ensure the geographical and environmental rationality of the selected centroid sub-region, the condition that it must be located within the community and not adjacent to isolated risk areas is set, effectively reducing the potential risks of the selected area. Furthermore, the restriction that its geological and hydrological parameters deviate from the community average by no more than 15% further ensures that the selected area is consistent with the community's representativeness in terms of environmental characteristics, thereby improving the accuracy and reliability of the dynamic safety factor calculation. Using the above methods, the centroid sub-region can more accurately reflect the actual situation of the community, providing a reliable basis for subsequent safety assessments.

[0090] The dynamic safety factor is compared with the stability threshold, and based on the comparison results, the stability level of each community and isolated risk area is classified. The specific logic behind this is as follows:

[0091] when When the community or isolated risk area is marked as stable, it means that the slope resistance force at the community or isolated risk area is significantly greater than the sliding force.

[0092] when When this occurs, the community or isolated risk area will be marked as an alert, indicating that enhanced monitoring and restrictions on entry will be necessary.

[0093] when When this occurs, the community or isolated risk area is marked as high-risk, indicating that localized landslides may occur and an emergency response plan needs to be activated.

[0094] when When this occurs, the community or isolated risk area is marked as unstable, indicating that a landslide has occurred or is imminent, and an evacuation alert is immediately triggered;

[0095] In the formula, express Dynamic safety factor at any given time. This is the preset stability threshold.

[0096] Step 3 determines the dynamic safety factor for each community and isolated risk zone based on the slope feature dataset. The advantage of this process is that it reflects the slope's stability status in real time under rainfall conditions. The introduction of the dynamic safety factor not only considers the influence of various environmental factors but also enables dynamic monitoring of each sub-region or community, allowing risk assessment to respond promptly to environmental changes. By comparing the dynamic safety factor with a stability threshold, the risk status of each area can be effectively classified, providing a clear basis for management.

[0097] Compared to existing technologies, the implementation of step 3 improves the real-time nature and accuracy of slope stability prediction. Traditional methods often rely on static or historical data for assessment, easily overlooking the impact of instantaneous events such as rainfall on slope stability. Step 3, through the calculation of a dynamic safety factor, makes the assessment results more timely and accurately reflects changes in the safety factor caused by factors such as rainfall. This mechanism provides an important basis for subsequent risk warning and decision-making, ensuring the scientific nature and effectiveness of slope management, thus playing a key role in promoting the overall plan and driving the establishment of a more refined and intelligent slope monitoring and management system.

[0098] Step 4: Establish a three-dimensional digital twin model of the target slope, accurately match the community division results with the model through a spatial mapping algorithm, and use different colors to identify the stability level of each community and isolated risk area in the visualization interface. For communities or isolated risk areas where the dynamic safety factor shows a monotonically decreasing trend over three consecutive monitoring periods, trigger a risk warning signal and highlight the evolution trajectory of the area in the three-dimensional digital twin model.

[0099] In this embodiment, a three-dimensional digital twin model of the target slope is constructed based on the BIM platform. The community division results are accurately matched with the model grid through spatial coordinate mapping. In the visualization interface, a four-color gradient rendering scheme is used to display the stability level of each community and isolated risk area in real time, and the real-time rainfall intensity distribution is overlaid. Among them, green, yellow, orange, and red represent stable state, warning state, high-risk state, and unstable state, respectively.

[0100] For areas where the dynamic safety factor decreases monotonically over three consecutive monitoring periods, an audible and visual early warning signal is automatically triggered. At the same time, the area is marked in the model with a pulse flashing effect, and an early warning report containing location coordinates, the rate of change of the dynamic safety factor, and the potential slip direction is generated. The system synchronously records the stability evolution trajectory of each area and supports displaying the landslide development process in a timeline playback manner.

[0101] Step 4 involves establishing a 3D digital twin model of the target slope and precisely matching the community delineation results with the model to achieve a visual representation of the slope's condition. The advantage of this process is that it not only intuitively displays the stability levels of different communities and isolated risk areas but also overlays rainfall intensity distribution in real time, providing users with comprehensive information support. Through the multi-color indicators in the visualization interface, decision-makers can quickly identify potential risk areas and take corresponding management measures, improving decision-making efficiency and response speed.

[0102] Compared to existing technologies, the implementation of step 4 significantly enhances the intelligence and operability of slope monitoring. Traditional methods often rely on static reports or single data views, which are insufficient to comprehensively reflect the dynamic changes of slopes. By introducing a three-dimensional digital twin model and combining it with real-time data, dynamic monitoring and visualization of slope conditions can be achieved, making risk assessment more scientific and accurate. This mechanism not only improves managers' understanding of slope stability but also provides intuitive evidence for early warning of potential risks and emergency response, thus playing a crucial role in the overall plan and promoting the modernization of slope monitoring and management.

[0103] Please see Figure 2 A slope stability prediction device under rainfall conditions, comprising:

[0104] The slope gridding modeling module is used to discretize the target slope into several sub-regions using a regular grid, assign regional attributes to each sub-region including geological parameters, hydrological parameters and topographic parameters, and integrate real-time rainfall intensity data provided by meteorological radar to form a slope feature dataset with spatiotemporal attributes.

[0105] The intelligent community division module is used to characterize the local slope information of each sub-region using multi-dimensional feature vectors based on the geological, hydrological and topographic parameters of each sub-region. It defines the regional coordination index between any two sub-regions based on the multi-dimensional feature vectors and performs clustering processing on the sub-regions using spectral clustering algorithm. The rest are marked as isolated risk areas, thereby dividing the target slope into multiple communities and isolated risk areas.

[0106] The dynamic safety assessment module is used to determine the dynamic safety factor of each community and isolated risk area based on the slope feature dataset, compare the dynamic safety factor with the stability threshold, and classify the stability level of each community and isolated risk area according to the comparison results; wherein, for each community, its centroid sub-region is selected as a representative to determine the dynamic safety factor of the community.

[0107] The 3D early warning visualization module is used to establish a 3D digital twin model of the target slope. It accurately matches the community division results with the model through a spatial mapping algorithm. In the visualization interface, the stability level of each community and isolated risk area is marked with different colors. For communities or isolated risk areas where the dynamic safety factor shows a monotonically decreasing trend over three consecutive monitoring periods, a risk warning signal is triggered. At the same time, the evolution trajectory of the area is highlighted in the 3D digital twin model.

[0108] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0109] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0110] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0111] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for predicting slope stability under rainfall conditions, characterized in that, The specific steps include: Step 1: Discretize the target slope into several sub-regions using a regular grid, assign regional attributes including geological parameters, hydrological parameters, and topographic parameters to each sub-region, and integrate real-time rainfall intensity data provided by meteorological radar to form a slope feature dataset with spatiotemporal attributes. Step 2: Based on the geological, hydrological and topographic parameters of each sub-region, use multidimensional feature vectors to characterize the local slope information of each sub-region, define the regional synergy index between any two sub-regions based on the multidimensional feature vectors, and combine the spectral clustering algorithm to cluster the sub-regions, thereby dividing the target slope into multiple communities and isolated risk areas. Step 3: Determine the dynamic safety factor for each community and isolated risk area based on the slope feature dataset, compare the dynamic safety factor with the stability threshold, and classify the stability level of each community and isolated risk area according to the comparison results; for each community, select its centroid sub-region as a representative to determine the dynamic safety factor of the community. Step 4: Establish a three-dimensional digital twin model of the target slope, accurately match the community division results with the model through a spatial mapping algorithm, and use different colors to identify the stability level of each community and isolated risk area in the visualization interface. For communities or isolated risk areas where the dynamic safety factor shows a monotonically decreasing trend over three consecutive monitoring periods, trigger a risk warning signal and highlight the evolution trajectory of the area in the three-dimensional digital twin model. The dynamic safety factor for each community and isolated risk zone is determined based on the slope feature dataset, using the following formula: In the formula, Indicates subregion in The dynamic safety factor at any given time is used to reflect the immediate stability state of the slope under rainfall conditions; The cohesion of the soil in the sub-region, is the unit weight of the soil in the sub-region, used to characterize the normal stress component generated by the self-weight of the sliding body. The sliding body refers to the part of the soil in the sub-region that can slide along the potential sliding surface. For the potential sliding surface depth, For the sub-region slope angle, Let be the pore water pressure in the subregion at time t. The surface curvature of the sub-region Let be the radius of curvature of the slope in the sub-region. The internal friction angle of the soil in the sub-region. The permeability coefficient is related to the water content. The saturated permeability coefficient is used to characterize the maximum permeability of soil when it is fully saturated, and is determined by indoor permeability tests. The current soil moisture content of the sub-region. Residual volumetric water content represents the percentage of water in the soil that cannot be drained by gravity, and is determined by the soil type. and These are the initial moisture content and the saturated moisture content, respectively. It is an empirical index used to control the rate at which the permeability coefficient changes with water content, and is related to the soil pore distribution; For each community, its centroid sub-region is selected as a representative to determine the community's dynamic safety coefficient. The method for selecting the centroid sub-region is as follows: First, calculate the average coordinates of the geometric centers of all sub-regions within the community as the centroid position. Then, select the sub-region with the closest Euclidean distance to this centroid position as the centroid sub-region. If multiple centroid sub-regions exist simultaneously, further compare the cosine similarity between their multidimensional feature vectors and the community's average features. Select the sub-region with the highest similarity as the centroid sub-region, which must satisfy the following condition: (1) Located within the community and not adjacent to isolated risk areas; (2) The deviations of its geological and hydrological parameters from the community average shall not exceed ; The dynamic safety factor is compared with the stability threshold, and based on the comparison results, the stability level of each community and isolated risk area is classified. The specific logic behind this is as follows: when When the community or isolated risk area is marked as stable, it means that the slope resistance force at the community or isolated risk area is significantly greater than the sliding force. when When this occurs, the community or isolated high-risk area will be marked as an alert, and monitoring will be intensified while restrictions are placed on entry. when When this occurs, the community or isolated risk area will be marked as high-risk, and the emergency response plan will be activated. when When this occurs, the community or isolated risk area is marked as unstable, indicating that a landslide has occurred or is imminent, and an evacuation alert is immediately triggered; In the formula, express Dynamic safety factor at any given time. This is the preset stability threshold.

2. The slope stability prediction method under rainfall conditions according to claim 1, characterized in that: The target slope is discretized into several sub-regions using a regular grid, where the grid size is determined based on the slope scale and monitoring accuracy requirements. to The adjustable range assigns regional attributes to each sub-region, including geological parameters, hydrological parameters, and topographic parameters; the geological parameters include permeability coefficient, internal friction angle, and cohesion; the hydrological parameters include initial water content, saturated water content, and real-time pore water pressure; and the topographic parameters include slope and surface curvature. By integrating real-time rainfall intensity data provided by meteorological radar and matching its spatiotemporal resolution with the grid division scale, a slope feature dataset with multidimensional features of time, space and attributes is finally formed, in which each parameter is stored in matrix form and a spatiotemporal index relationship is established. Geological, hydrological, and topographic parameters were obtained through field surveys, sensor monitoring, and remote sensing measurements, serving as regional attributes for each sub-region.

3. The slope stability prediction method under rainfall conditions according to claim 2, characterized in that: Based on the geological, hydrological, and topographic parameters of each sub-region, a multidimensional feature vector is constructed for each sub-region. The expression for the multidimensional feature vector is as follows: In the formula, sub-region The multidimensional feature vectors, For the index of the sub-region, , and Representing sub-regions Geological parameters, hydrological parameters, and topographic parameters, , and Sub-regions in sequence The permeability coefficient, internal friction angle, and cohesion, , and Sub-regions in sequence The initial water content, saturated water content, and real-time pore water pressure, and Sub-regions in sequence The slope and surface curvature; The regional synergy index between any two sub-regions is defined based on multidimensional feature vectors, and the formula used is as follows: In the formula, Subregion and subregions Regional synergy index and The index is for the sub-region, and ; , and Representing sub-regions and subregions Differences in geological features, hydrological features, and topographic features between them; , and Representing sub-regions Geological parameters, hydrological parameters, and topographic parameters, , and Sub-regions in sequence The permeability coefficient, internal friction angle, and cohesion, , and Sub-regions in sequence The initial water content, saturated water content, and real-time pore water pressure, and Sub-regions in sequence The slope and surface curvature, , and For the preset weights, And satisfy .

4. The slope stability prediction method under rainfall conditions according to claim 3, characterized in that: The specific logic behind using spectral clustering algorithms to cluster sub-regions is as follows: A regional synergy index matrix is ​​constructed based on the regional synergy index among all sub-regions. A spectral clustering algorithm is then used to divide the sub-regions into communities. Specifically, the Laplace matrix of the regional synergy index matrix is ​​calculated, and the optimal number of communities is determined through eigenvalue decomposition. The K-means algorithm was used to divide the subregion into Individual communities; setting dynamic similarity thresholds. This results in the average regional synergy index among sub-regions within the community being less than [a certain value]. The average regional synergy index among sub-regions of the community is greater than For any sub-region, if its regional synergy index with all other sub-regions is greater than or equal to the dynamic similarity threshold... If so, it is determined to be an isolated risk area; Repeat the above similarity judgment until the community affiliation of all sub-regions no longer changes, thus forming the final community division result.

5. The method for predicting slope stability under rainfall conditions according to claim 1, characterized in that: A three-dimensional digital twin model of the target slope is constructed based on the BIM platform. The community division results are accurately matched with the model grid through spatial coordinate mapping. In the visualization interface, a four-color gradient rendering scheme is used to display the stability level of each community and isolated risk area in real time, and the real-time rainfall intensity distribution is overlaid. Among them, green, yellow, orange and red represent stable state, warning state, high-risk state and unstable state, respectively. For areas where the dynamic safety factor decreases monotonically over three consecutive monitoring periods, an audible and visual early warning signal is automatically triggered. At the same time, the area is marked in the model with a pulse flashing effect, and an early warning report containing location coordinates, the rate of change of the dynamic safety factor, and the potential slip direction is generated. The system synchronously records the stability evolution trajectory of each area and supports displaying the landslide development process in a timeline playback manner.

6. A slope stability prediction device under rainfall conditions, characterized in that: The slope stability prediction device under rainfall conditions is used to execute the slope stability prediction method under rainfall conditions according to any one of claims 1-5, comprising: The slope gridding modeling module is used to discretize the target slope into several sub-regions using a regular grid, assign regional attributes to each sub-region including geological parameters, hydrological parameters and topographic parameters, and integrate real-time rainfall intensity data provided by meteorological radar to form a slope feature dataset with spatiotemporal attributes. The intelligent community division module is used to characterize the local slope information of each sub-region using multi-dimensional feature vectors based on the geological, hydrological and topographic parameters of each sub-region. Based on the multi-dimensional feature vectors, it defines the regional coordination index between any two sub-regions and combines the spectral clustering algorithm to perform clustering processing on the sub-regions, thereby dividing the target slope into multiple communities and isolated risk areas. The dynamic safety assessment module is used to determine the dynamic safety factor of each community and isolated risk area based on the slope feature dataset, compare the dynamic safety factor with the stability threshold, and classify the stability level of each community and isolated risk area according to the comparison results; wherein, for each community, its centroid sub-region is selected as a representative to determine the dynamic safety factor of the community. The 3D early warning visualization module is used to establish a 3D digital twin model of the target slope. It accurately matches the community division results with the model through a spatial mapping algorithm. In the visualization interface, the stability level of each community and isolated risk area is marked with different colors. For communities or isolated risk areas where the dynamic safety factor shows a monotonically decreasing trend over three consecutive monitoring periods, a risk warning signal is triggered. At the same time, the evolution trajectory of the area is highlighted in the 3D digital twin model.

Images