20 results about "Landslide susceptibility" patented technology

The present application relates to the technical field of geological disaster risk assessment, and discloses a landslide-prone prediction method based on multi-scale geographic weighted regression and spatial heterogeneity partitioning, which solves the problems of low local accuracy, poor area efficiency and insufficient prediction stability caused by single spatial scale, uniform modeling and single evaluation system in traditional landslide prediction models. The present application organically combines multi-scale geographic weighted regression with spatial heterogeneity partitioning, first adaptively assigns a dedicated optimal bandwidth to each disaster-inducing factor through a multi-scale regression model to accurately depict the spatial non-stationary characteristics of landslide disaster-inducing relationships, then reconstructs the discrete regression coefficients into a spatial continuous surface with the help of Kriging interpolation, dynamically extracts the dominant factors with the optimal discrete and natural discontinuity method to realize the heterogeneity partitioning of the study area, takes each partition as an independent unit to carry out landslide-prone deduction, and constructs a multi-dimensional comprehensive evaluation system from the dimensions of prediction accuracy, area rationality and uncertainty robustness.

The application discloses a landslide susceptibility comprehensive evaluation method, system, device, medium and product, relates to the technical field of geological disaster prediction, and the method comprises the steps: taking the SBAS-InSAR deformation rate as a dynamic deformation factor, combining a static environmental factor, and constructing an original feature dataset; adopting a recursive feature elimination algorithm, performing importance sorting and iterative elimination on evaluation factors in the original feature dataset, determining an optimal feature subset, training an RFE-RF-XGBoost cascade integrated model; inputting the optimal feature subset corresponding to all grid units in the research area into the trained RFE-RF-XGBoost cascade integrated model, determining a landslide susceptibility spatial classification map, verifying and locally correcting different risk level regions divided in the landslide susceptibility spatial classification map, and determining a landslide susceptibility evaluation result, so that the timeliness and accuracy of the landslide susceptibility evaluation result are improved.

This invention provides a method and related equipment for assessing earthquake landslide susceptibility. Multiple landslide influencing factors are selected from multi-source data of the study area, and multicollinearity analysis and Pearson correlation coefficient analysis are performed on all landslide influencing factors to obtain basic environmental factors. Newmark displacement is calculated based on the physical and mechanical parameters in the multi-source data and the basic environmental factors. The Newmark displacement is stacked with the basic environmental factors to obtain multi-channel image data, which is then input into an earthquake landslide susceptibility assessment model for evaluation, resulting in a coseismic landslide susceptibility zoning map of the study area. Compared with existing technologies, this invention uses Newmark displacement as an independent feature input, compensating for the lack of physical mechanism support in traditional pure data-driven models. It achieves the complementary advantages of geological disaster dynamics mechanisms and deep learning feature extraction capabilities, improving the accuracy and reliability of earthquake landslide susceptibility assessment.

The application discloses a landslide susceptibility prediction method combining terrain combined features and partition explainable analysis, and relates to the technical field of geological disaster evaluation. Slope, plane curvature and profile curvature factors are extracted from a digital elevation model of a research area, and after standardization, Gaussian mixture model is used for unsupervised clustering. The class labels obtained by clustering are taken as terrain combined features and are coded, and are combined with landslide influence factors to form an input feature set. The input feature set is input into an XGBoost model for training and the hyperparameters are optimized through grid search. Based on the trained model, the SHAP method is used to calculate the global feature contribution degree, and the contribution degrees of various factors are calculated according to terrain combination types, and the spatial differences of the factors under different terrain units are analyzed. The terrain types obtained by clustering are used as explicit features to participate in model training, and the spatial heterogeneity of the factors is revealed through grouped contribution degree analysis, which provides a new technical means for landslide susceptibility evaluation.

This invention belongs to the field of risk prediction technology for mountainous cities, and discloses a CNN-based method for quantifying and predicting landslide susceptibility in mountainous cities by integrating multi-source data. The specific steps are as follows: Step 1: Multi-source data collection and processing, collecting remote sensing image data, geological data, topographic data, and building data. This invention achieves deep fusion of multi-source data by integrating remote sensing images, geological maps, topographic data, building distribution, and other multi-dimensional data; it automatically extracts deep features from the data through the convolutional and pooling layers of CNN, eliminating the need for manual feature design and improving feature extraction capabilities; through the construction of a CNN model that integrates heterogeneous data fusion and multi-source data fusion, it can directly capture spatial neighborhood relationships, improving spatial correlation; compared with traditional techniques, this method significantly improves the accuracy and robustness of landslide susceptibility prediction in complex mountainous cities through multi-source data complementarity and deep feature extraction.

The application provides a slope unit division and landslide susceptibility evaluation method, and belongs to the technical field of data processing, and specifically comprises the following steps: generating basic data required for slope unit division and susceptibility evaluation; identifying and skeletonizing the terrain boundary information of a study area based on the basic data; establishing a spatial connection relationship based on the terrain skeleton to form a closed initial catchment area; optimizing and integrating the initial catchment area in combination with terrain and hydrological constraints to obtain a final slope unit division result; extracting various evaluation factors required for landslide susceptibility evaluation based on the final slope unit, and constructing evaluation sample data; establishing a susceptibility evaluation model by using the evaluation sample, and training and optimizing the model parameters; and using the optimized susceptibility evaluation model to carry out prediction analysis on the slope units in the study area, and outputting the landslide susceptibility evaluation result. Through the scheme of the application, the evaluation efficiency, accuracy and adaptability are improved.

The embodiment of the invention discloses a disaster-pregnant environment constrained landslide susceptibility evaluation method and device, equipment and a medium. The method comprises the following steps: constructing a slope unit based on a curve water rate watershed method and generating a plurality of geographic nodes; extracting attribute features of each geographic node in a spatial statistics mode; constructing a directed weighted graph associated with the landslide and the disaster-pregnant environment in combination with the environment feature constraint and the node feature constraint; wherein the environment feature constraint represents environment consistency between any two geographic nodes, and the node feature constraint represents attribute feature similarity between any two geographic nodes; and based on the directed weighted graph, carrying out landslide susceptibility evaluation by using the trained graph neural network model. On the basis of a graph neural network method for fully associating a landslide with a disaster-pregnant environment graph structure, potential association features of the landslide are deeply mined, landslide susceptibility evaluation of graph nodes is realized, the false alarm rate and the missed alarm rate of the landslide are reduced, and the reliability of landslide susceptibility evaluation is improved.

This application provides a method and system for assessing earthquake-induced landslide risk in transportation networks in high-intensity seismic zones, relating to the field of landslide risk assessment technology. The method includes: screening key influencing factors of earthquake-induced landslides; optimizing the construction of positive and negative sample libraries; using a spatial weighted machine learning model to evaluate landslide susceptibility and generate a susceptibility zoning map; extracting parameters of potential landslide source areas based on the high-susceptibility zone identification results; using a parallel particle discrete element method to simulate the entire landslide movement process to obtain hazard parameters; inputting the hazard parameters into a transportation engineering structure vulnerability model to quantitatively calculate the failure probability; and fusing the susceptibility probability and structural vulnerability results to generate a risk zoning map based on road network units. The final results of this application are directly applicable to the operation and maintenance management of transportation infrastructure. The provided risk zoning map can be directly used to guide the optimal allocation of risk control resources, the formulation of emergency plans, and the seismic resilience design of engineering projects, demonstrating clear application value.

The application discloses a landslide susceptibility assessment method, device, equipment and medium, and relates to the technical field of water conservancy and geotechnical engineering risk control research, and the method comprises the steps of: constructing a landslide database of an area to be evaluated, selecting a plurality of landslide influence factors from the landslide database, and quantitatively processing each landslide influence factor by using a frequency ratio method; selecting the same number of non-landslide points as landslide points in the area to be evaluated to form a sample set; training a plurality of machine learning algorithms by using the training set to construct a landslide susceptibility model corresponding to each machine learning algorithm; calculating the feature weight of each landslide influence factor in each landslide susceptibility model by using Shapley additive theory; and calculating the landslide susceptibility value corresponding to each landslide susceptibility model by using a preset weighting rule to assess the landslide susceptibility of the area to be evaluated. The application determines the objective proportion of each influence factor in the assessment, and the assessment result is interpretable.

This invention discloses an intelligent assessment method for landslide susceptibility based on geomorphic fractal heterogeneity, belonging to the field of geological disaster prediction technology. The method includes: collecting multi-source geographic data and constructing a landslide evaluation index system covering four core factors: topography, hydrology, spatial location, and land cover; performing double normalization on the original features to eliminate dimensional differences and maintain data distribution stability; dividing the features into multiple fractal subsets according to the geomorphic formation mechanism, and constructing heterogeneous base learners such as CatBoost, XGBoost, and Random Forest to achieve independent modeling of features in each subset; using a soft-voting weighted fusion strategy to adaptively integrate the prediction probabilities of different base learners to generate an initial probability of landslide susceptibility; dynamically optimizing the selection threshold on the validation set with the goal of maximizing the F1 score, and outputting the final risk level. This invention, through a technical architecture of "landform fractal grouping + heterogeneous collaborative integration + dynamic threshold optimization", fully explores the multidimensional nonlinear coupling law of landslide formation, significantly improves prediction accuracy and generalization ability. In the case data, the AUC reached 0.8832, which comprehensively surpasses the single benchmark model and can provide a reliable basis for disaster prevention and mitigation in mountainous areas.

This disclosure relates to a landslide susceptibility assessment method based on heterogeneous ensemble learning considering spatial heterogeneity, and belongs to the field of risk prediction for landslide disasters. According to the method, a zoning strategy is adopted to fully explore the spatial heterogeneity of landslide assessment factors; besides, dominant influencing factors of landslide development in different zoned regions and the whole region are revealed; and on this basis, a heterogeneous ensemble learning model is constructed to assess the landslide susceptibility. This disclosure can realize accurate landslide prediction.

This invention relates to a landslide susceptibility assessment method based on spatiotemporal enhancement and heterogeneous integration, belonging to the field of geological disaster prediction technology. First, spatiotemporal benchmark unification and sample balancing are constructed using multi-source heterogeneous geospatial data of the study area. Then, a three-level progressive framework of "heterogeneous base learner – meta-feature secondary encoding – dual-channel deep cross-fusion" is used as the core. Three heterogeneous base learners—random forest, XGBoost, and LightGBM—are used to output leak-free meta-probability features through temporal cross-folding. Next, the original high-dimensional factors and meta-features are input into a deep sub-network via a "spatial-semantic" dual-channel approach, and cross-fusion is completed using adaptive gating weights. Finally, the landslide occurrence probability is output. Experiments show that this method outperforms traditional single models in multiple metrics such as ROC and PR, and can significantly improve the accuracy and robustness of susceptibility mapping without increasing field survey costs, providing a highly reliable decision-making basis for mountainous land spatial planning and early disaster warning.

The application discloses a landslide susceptibility intelligent evaluation method based on feature stability guidance and cost adaptive tightening, which comprises the following steps: collecting and normalizing landslide sample data; calculating feature importance and sorting by random forest; traversing feature subset scale by gradient boosting tree, determining global optimal subset by cross-validation AUC; calculating feature stability coefficient, generating tightening priority queue; trying to remove features in turn by asymmetric cost-sensitive AUC measurement, and accepting if the performance decline is not more than the threshold; adaptively adjusting the threshold and re-tightening after the confrontation verification, recording the historical optimal subset; retraining the model to output the landslide probability. The application realizes feature stability guidance, asymmetric cost-sensitive tightening and self-evolution threshold closed loop, reduces redundant features while maintaining accuracy, and improves generalization and interpretability. The measured AUC reaches 0.897, which is 3.2% higher than that of the traditional GBDT, and the feature is reduced by 40%.

This invention provides a method and system for predicting the susceptibility of railway landslides, belonging to the field of geological disaster monitoring and railway engineering safety control technology. This method comprehensively applies technologies such as geographic information analysis, GNSS high-precision deformation monitoring, Internet of Things sensing, temporal modeling, and deep learning to dynamically assess the instability risk of railway slopes under complex geological and meteorological conditions. By constructing a spatial susceptibility model and a temporal triggering model, and fusing them to form a comprehensive risk index, it achieves intelligent early warning of the entire process of railway landslides, from long-term potential identification to short-term triggering prediction. This invention can be widely applied to geological disaster monitoring, risk zoning, and safety protection in mountainous railways, highways, and major linear engineering projects.

The present application relates to the technical field of geological disaster risk assessment, and discloses a landslide susceptibility evaluation method based on optimal similarity constraint of geographical environment, which solves the problems of feature aliasing of positive and negative samples, low model recognition accuracy and poor robustness of evaluation results in the existing landslide susceptibility evaluation due to the dependence of negative sample selection on spatial geometry / single terrain index and the failure to remove positive sample noise. The present application scheme is summarized as follows: a multi-dimensional disaster-prone feature space is constructed by fusing multi-source geographic spatial data, and the multi-dimensional geographical environment comprehensive similarity of the calculation unit and the landslide point is calculated; the optimal representative observation benchmark is determined by nested cross-validation iteration optimization, the global landslide density is inversely inferred and mapped into non-landslide credibility; balanced negative samples are extracted in the high credibility safety area, and a machine learning model is trained to complete the evaluation. The present application can improve the model recognition accuracy and evaluation stability, and is suitable for regional landslide susceptibility evaluation in complex geological environment.

This invention discloses a method for simulating landslide susceptibility based on binocular camera technology combined with deep learning algorithms and finite element analysis. The method uses a UAV's binocular camera to collect high-precision 3D topographic data of landslide-prone areas, and combines this data with remote sensing to detect soil and vegetation physical properties to construct a 3D solid model. Coupled with real rainfall scenarios, a deep learning algorithm is used to optimize the rainfall intensity-soil cohesion correlation model, simulating various real rainfall conditions. Continuous displacement data of the landslide surface is extracted and imported into the finite element model, enabling dynamic simulation of the entire process of a landslide from local deformation to overall collapse and the formation of a new steady state. Simultaneously, model optimization and landslide susceptibility assessment are completed. This invention links existing monitoring technologies with mechanical simulation, solving the problem of inaccurately representing the dynamic evolution of landslides, and providing precise technical support for landslide disaster early warning and prevention.

This invention discloses a landslide susceptibility assessment method based on a heterogeneous integrated dual-channel network, belonging to the field of geological disaster prediction technology. This method constructs a multi-source heterogeneous evaluation factor system encompassing topography, geology, and environment. It employs HistGradientBoosting, XGBoost, and CatBoost heterogeneous primary learners for K-fold out-of-fold meta-feature extraction, addressing the problem of insufficient information representation by single models. Furthermore, it constructs a dual-channel deep network consisting of "original feature 1D-CNN + attention" and "meta-feature Bi-LSTM + self-attention," achieving complementary fusion of static environmental variables and dynamic model confidence, significantly improving the model's ability to identify hidden landslide hazards. Finally, it generates a five-level susceptibility zoning map based on GIS raster computation and the natural breakpoint method. Experiments validated in typical mountainous areas showed an AUC of 0.899, outperforming traditional single and conventional Stacking models, providing high-precision technical support for land planning and disaster prevention in mountainous areas.

The application discloses a landslide susceptibility intelligent evaluation method and device based on a physical guidance gated graph attention network, and belongs to the technical field of geological disaster risk assessment. The method comprises the following steps: acquiring target region sample point data, including geographic position coordinates, slope physical attributes, disaster-causing factors and historical landslide labels; adopting a k nearest neighbor algorithm to construct a space graph structure based on geographic positions, and taking distance reciprocals as edge weights; inputting the disaster-causing factors as node features into a gated graph attention network; the network calculates original attention coefficients through a graph attention sublayer, and generates dynamic gating values driven by the slope physical attributes, so that gated attention weights are obtained by combination to aggregate neighbor information, and landslide occurrence probabilities are output; and the probabilities are used to divide susceptibility grades and generate a zoning map. The application embeds physical knowledge into a model in the form of structural constraints, avoids feature collinearity interference, and significantly improves spatial heterogeneity fitting capability, evaluation precision and physical interpretability.

The application discloses a landslide susceptibility multi-source heterogeneous data fusion and parallel deep network evaluation method, and belongs to the field of geological disaster prediction. The method does not increase the cost of field investigation, and constructs a "3+1" cascade framework: firstly, the multi-source heterogeneous geographic spatial data of the research area is subjected to coordinate unification, resampling and multiple collinearity filtering; then, a parallel heterogeneous basic learner group, gradient boosting tree, extremely random tree and adaptive boosting, extracts first-level element features through a no-leakage out-of-fold method; at the same time, the normalized grid data is reshaped into a space-time tensor and input into a "double-tower" deep network, wherein tower A is a 1D-CNN + attention gate channel, tower B is a fully connected element feature channel, and the landslide occurrence probability is output after the two towers are fused; finally, the probability graph is divided into five levels of susceptibility by using the natural breakpoint method, and the accuracy is tested by three indexes of ROC-AUC, PR-AP and spatial hit rate. The application explicitly separates the basic learner group and the deep network, retains the interpretability and improves the nonlinear representation ability, and is suitable for early identification of regional landslide hazards and land space planning.