Accurate prediction of ground subsidence is of great significance for the prevention and mitigation of this type of geological disaster. It is still a challenge when wide area is concerned. In this article, a heterogeneous long short-term memory (HLSTM) network is proposed for large-scale ground subsidence prediction based on interferometric synthetic aperture radar (InSAR) data. First, the study area is divided into homogeneous subregions through spatial clustering of InSAR-derived subsidence velocity. Second, a specific LSTM model is constructed to capture complex nonlinear temporal correlations embedded in InSAR-derived subsidence time series for each subregion. Essentially both spatial heterogeneity and temporal correlation are incorporated into the HLSTM prediction. In the experiment part, the HLSTM predictor is validated using a subsidence monitoring result from 80 Sentinel-1 images acquired over Cangzhou, China, from 2017 to 2019. The HLSTM result shows the highest prediction accuracy through comparisons with the results from other seven methods.

Landslide susceptibility mapping (LSM) constitutes a valuable analytical instrument for estimating the likelihood of landslide occurrence, thereby furnishing a scientific foundation for the prevention of natural hazards, land-use planning, and economic development in landslide-prone areas. Existing LSM methods are predominantly data-driven, allowing for significantly enhanced monitoring accuracy. However, these methods often overlook the consideration of landslide mechanisms and uncertainties associated with non-landslide samples, resulting in lower model reliability. To effectively address this issue, a knowledge-guided landslide susceptibility assessment framework is proposed in this study to enhance the interpretability and monitoring accuracy of LSM. First, a landslide knowledge graph is constructed to model the relationships between landslide entities and summarize landslide susceptibility rules. Next, combining the obtained landslide rules with geographic similarity principles, high-confidence non-landslide samples are selected to optimize the quality of the samples. Subsequently, a Landslide Knowledge Fusion Cell (LKF-Cell) is utilized to couple landslide data with landslide knowledge, resulting in the acquisition of informative and semantically rich landslide event features. Finally, a precise and credible landslide susceptibility assessment model is built based on a convolutional neural network (CNN), and landslide susceptibility spatial distribution levels are mapped. The research findings indicate that the CNN-based model outperforms traditional machine learning algorithms in predicting landslide probability; in particular, the Area Under the Curve (AUC) of the model was improved by 3–6% after sample optimization, and the AUC value of the LKF-Cell method was 6–11% higher than the baseline method.

Landslide hazard assessment is essential for determining the probability of landslide occurrence in a specific spatial and temporal range. The hazard assessment of potential landslides could support landslide disaster early warning and disaster prevention decisions, which have important guiding significance for urban construction and sustainable development. Due to the lack of consideration of the synergistic effect of multiple factors and geographic scene heterogeneity, the accuracy of existing landslide hazard assessment methods still needs to be improved, and the interpretability and applicability of existing models still need to be improved. In this paper, we propose a landslide hazard assessment method considering the synergistic effect of multiple factors, including natural factors and human activities, and the heterogeneity of geographic scenes. On this basis, we carry out experimental verification on rainfall–induced landslides in Dehong Prefecture, Yunnan Province, China. Firstly, rainfall–induced landslide hazards’ characteristics and impact factors are analyzed and classified. The whole study area is divided into some homogeneous sub–regions using regional dynamic constraint clustering based on the similarity of underlying environmental variables. Then, considering the spatial autocorrelation between various landslide conditioning and trigger factors, a local weighted random forest model is developed to evaluate the rainfall–induced landslide hazards comprehensively. Experimental results show that the proposed method has higher accuracy and interpretability than the existing representative methods and can provide useful references for preventing landslide hazards.

Landslides triggered by rainfall are complex phenomena influenced by a multitude of condition and trigger factors. A significant challenge in the field is the accurate and interpretable assessment of large-scale landslide hazards, particularly due to the lack of consideration for the synergistic effects of multiple triggers and spatial heterogeneity. This study introduces a novel regional hazard assessment method that leverages geographic similarity to address these challenges. Our approach consists of four key steps: (1) extraction of sample information from relevant data based on the historical distribution of landslides and their influencing factors, (2) application of a scale-space algorithm to manage spatial heterogeneity, with a partition scale determined by the q-value variation, (3) optimization of sample configuration and generation criteria under the guidance of geographic similarity for enhanced spatiotemporal modeling, and (4) utilization of machine learning models to refine inductive bias and capture nonlinear relationships, enabling a quantitative estimation of hazard probabilities for each slope unit within the prediction module. We applied our P-RF + method to Yunnan Province, China, incorporating 11 condition factors and 7 trigger factors across 624 historical rainfall-induced landslides and 1248 non-landslide cases. Comparative experiments reveal that the P-RF + model substantially outperforms existing methods in accuracy and interpretability. Furthermore, a case study during the rainy season illustrates the model's capability to provide timely warning instructions for rainfall-induced landslides. These findings underscore the potential of our proposed method to offer valuable insights for disaster prevention decision-making. Graphical Abstract

Landslide hazard assessment denotes the systematic evaluation of the likelihood of landslide occurrence within a defined temporal and spatial context. Rainfall-induced landslide hazard assessment methods often fail to adequately consider the impacts of human activities, resulting in assessments that lack sufficient accuracy to meet practical demands. This study proposes an innovative dynamic assessment model that integrates both environmental factors and triggering factors, enabling regional hazard evaluations that account for the dual spatial constraints imposed by slopes and hazard-bearing bodies. The study proposes an objective estimation model for quantifying human activity intensity, utilizing the Criteria Importance Through Intercriteria Correlation (CRITIC) method and the Entropy Weight Method (EWM). Subsequently, random forest and Transformer models were employed to perform a progressive assessment of landslide susceptibility and hazard. Specifically, the dynamic assessment of rainfall-induced landslide hazard incorporated human activity intensity and rainfall characteristics as key triggering factors. The case study carried out in Zhenyuan County indicates that the model substantially improves and significantly increases the accuracy of disaster warnings and reduces the required hazard assessment area by approximately 40.6%, offering a targeted and valuable reference for early warning systems and decision-making of rainfall-induced landslides.