Landslide susceptibility mapping is considered to be a prerequisite for landslide prevention and mitigation. However, delineating the spatial occurrence pattern of the landslide remains a challenge. This study investigates the potential application of the stacking ensemble learning technique for landslide susceptibility assessment. In particular, support vector machine (SVM), artificial neural network (ANN), logical regression (LR), and naive Bayes (NB) were selected as base learners for the stacking ensemble method. The resampling scheme and Pearson’s correlation analysis were jointly used to evaluate the importance level of these base learners. A total of 388 landslides and 12 conditioning factors in the Lushui area (Southwest China) were used as the dataset to develop landslide modeling. The landslides were randomly separated into two parts, with 70% used for model training and 30% used for model validation. The models’ performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) and statistical measures. The results showed that the stacking-based ensemble model achieved an improved predictive accuracy as compared to the single algorithms, while the SVM-ANN-NB-LR (SANL) model, the SVM-ANN-NB (SAN) model, and the ANN-NB-LR (ANL) models performed equally well, with AUC values of 0.931, 0.940, and 0.932, respectively, for validation stage. The correlation coefficient between the LR and SVM was the highest for all resampling rounds, with a value of 0.72 on average. This connotes that LR and SVM played an almost equal role when the ensemble of SANL was applied for landslide susceptibility analysis. Therefore, it is feasible to use the SAN model or the ANL model for the study area. The finding from this study suggests that the stacking ensemble machine learning method is promising for landslide susceptibility mapping in the Lushui area and is capable of targeting areas prone to landslides.

In the landslide chain from pre-disaster conditions to landslide mitigation and recovery, time is an important factor in understanding the geological hazards process and managing landsides. Static knowledge graphs are unable to capture the temporal dynamics of landslide events. To address this limitation, we propose a systematic framework for constructing a multi-temporal knowledge graph of landslides that integrates multi-source temporal data, enabling the dynamic tracking of landslide processes. Our approach comprises three key steps. First, we summarize domain knowledge and develop a temporal ontology model based on the disaster chain management system. Second, we map heterogeneous datasets (both tabular and textual data) into triples/quadruples and represent them based on the RDF (Resource Description Framework) and quadruple approaches. Finally, we validate the utility of multi-temporal knowledge graphs through multidimensional queries and develop a web interface that allows users to input landslide names to retrieve location and time-axis information. A case study of the Zhangjiawan landslide in the Three Gorges Reservoir Area demonstrates the multi-temporal knowledge graph’s capability to track temporal updates effectively. The query results show that multi-temporal knowledge graphs effectively support multi-temporal queries. This study advances landslide research by combining static knowledge representation with the dynamic evolution of landslides, laying the foundation for hazard forecasting and intelligent early-warning systems.

Traditional landslide susceptibility assessment (LSA) methods typically adopt a global modeling strategy, which struggles to account for the pronounced spatial heterogeneity arising from variations in topography, geology, and vegetation conditions within a region. Furthermore, model predictive performance is often undermined by feature redundancy. To address these limitations, this study focuses on the landslide disaster early-warning demonstration area in Honghe Prefecture, Yunnan Province. It proposes an ensemble learning model termed heterogeneity feature optimized stacking (HF-stacking), which integrates spatial heterogeneity partitioning (SHP) with feature selection to improve the scientific rigor of LSA. This method initially establishes an LSA system comprising 15 static landslide conditioning factors (LCFs) and two dynamic factors representing the average annual deformation rates derived from interferometric synthetic aperture radar (InSAR) technology. Based on landslide inventory data, an SHP method combining t-distributed stochastic neighbor embedding (t-SNE) and iterative self-organizing (ISO) clustering was developed to divide the study area into subregions. Within each subregion, a tailored feature selection strategy was applied to determine the optimal feature subset. The final LSA was performed using the stacking ensemble learning approach. The results show that the HF-stacking model achieved the best overall performance, with an average AUC of 95.90% across subregions, 4.23% higher than the traditional stacking model. Other evaluation metrics also demonstrated comprehensive improvements. This study confirms that constructing an SHP framework and implementing feature selection strategies can effectively reduce the impact of spatial heterogeneity and feature redundancy, thereby significantly enhancing the predictive performance of LSA models. The proposed method contributes to improving the reliability of regional landslide risk assessments.

In response to the shortage of theoretical support for negative sample selection and the imbalance between positive and negative samples in landslide susceptibility assessment (LSA), this study presents a dual optimization framework of sampling strategy and sample ratio based on the frequency ratio (FR) model and evaluates its performance in the Heishui River Basin using the random forest (RF) model. At the level of negative sample optimization, FR is used to quantify the spatial associations between landslides and environmental factors, delineate non-landslide zones as the source region for negative samples, and systematically compare the performance of five sampling strategies—random, buffer-zone, low-slope, low-density, and FR-optimized sampling. At the level of ratio adjustment, an innovative positive–negative sample ratio model based on the area ratio between susceptible and non-susceptible zones (1:1.3) is proposed, and four additional schemes (1:1, 1:2, 1:2.5, and 1:3) are designed for comparison. The results show that the FR-optimized sampling strategy provides the best discriminative performance, with AUC (area under the curve) = 0.992, Kappa = 0.964, accuracy = 0.982, and F1 score = 0.982, and achieves the highest mean metric value (0.980) and the lowest standard deviation (0.008). The 1:1.3 ratio scheme maintains the highest mean performance (0.982) and the lowest standard deviation (0.007), while yielding the optimal Kappa (0.968) and F1 score (0.982), confirming its advantages in classification balance and model stability. Spatial prediction results indicate that very high and high susceptibility zones are concentrated along both sides of the middle and lower reaches of the Heishui River Basin, occupying only 18.52% of the total area but containing 98.38% of the mapped landslide points, which strongly supports the reliability of the proposed model in identifying landslide risk hotspots. The proposed dual optimization framework not only enhances the robustness of susceptibility mapping but can also be directly applied to risk screening for territorial spatial planning and engineering development in the Heishui River Basin.