Landslide displacement prediction is an essential base of landslide hazard prevention, which often needs to establish an accurate prediction model. To achieve accuracy prediction of landslide displacement, a displacement prediction model based on a salp-swarm-algorithm-optimized temporal convolutional network (SSA-TCN) is proposed. The TCN model, consisting of a causal dilation convolution layer residual block, can flexibly increase the receptive fields and capture the global information in a deeper layer. SSA can solve the hyperparameter problem well for TCN model. The Muyubao landslide displacement collected from a professional GPS monitoring system implemented in 2006 is used to analyze the displacement features of the slope and evaluate the performance of the SSA-TCN model. The cumulative displacement time series is decomposed into trend displacement (linear part) and periodic displacement (nonlinear part) by the variational modal decomposition (VMD) method. Then, a polynomial function is used to predict the trend displacement, and the SSA-TCN model is used to predict the periodic displacement of the landslide based on considering the response relationship between periodic displacement, rainfall, and reservoir water. This research also compares the proposed approach results with the other popular machine learning and deep learning models. The results demonstrate that the proposed hybrid model is superior to and more effective and accurate than the others at predicting the landslide displacement.

Landslide hazard assessment is an important component of risk management and land-use planning. This study aims to investigate the application of a physically-based model named after the fast shallow landslide assessment model (FSLAM) to rainfall-triggered landslide hazard assessment. In August 2015, a total of 123 landslides induced by Typhoon Soudelor in Wenzhou City, southeastern China, was taken as an example. Five input raster files (elevation, soil types, vegetation, antecedent rainfall, event rainfall) and two parameter files regarding soil properties and vegetation were determined. Considering the randomness and uncertainty of soil and vegetation parameters on the regional scale, FSLAM model computes the probability of failure (PoF) by using random parameters inputs. Finally, the landslide hazard map was generated for the study area to reflect the landslide risk. The results showed that FSLAM could accurately capture the effect of rainfall on PoF of slopes, and more than 70% of the landslide were identified in very high/high hazard zones. The accuracy of the receiver operating characteristic (ROC) reached 0.720, which was higher than that of the Transient Rainfall Infiltration and Grid-Based Regional Slope-Stability (TRIGRS) model (0.620). Regarding the computational time, FSLAM had better efficiency, and the consuming time was 1/25 compared with TRIGRS.

Landslide susceptibility assessment is considered the first step in landslide risk assessment, but current studies mostly rely on GIS platforms or other software for data preprocessing. The modeling process is relatively complicated and multi-models cannot be integrated. With regard to this issue, this study develops a Python system for automatic assessment of regional landslide susceptibility. The Python system implements landslide susceptibility assessment through three modules: geographic data processing, machine learning modeling and result evaluation analysis. For geographic data processing, ten landslide influencing factors can be used to construct an evaluation factor dataset and reclassify the thematic maps based on the frequency ratio method. Four built-in machine learning models (logistic regression (LR), multi-layer perceptron (MLP), support vector machine (SVM) and extreme gradient boosting (XGBoost)) are integrated into the system to complete susceptibility modeling and calculation. Additionally, receiver operating characteristic (ROC) curves can be automatically generated to evaluate the accuracy. The system was then applied into Lantian County in Shaanxi Province as a demonstration example. The results show that the areas under the ROC curve (AUC) of the four models are 0.838 (LR)、0.882 (SVM)、0.809 (MLP) and 0.812 (XGBoost), respectively, indicating that the SVM model was the most suitable model for landslide susceptibility assessment in Lantian County in the Loess Plateau of China. The system has now been made open source on Github, which can effectively improve the efficiency of regional landslide susceptibility assessment, especially provide tools for data processing and modeling for non-professionals.

Landslide displacement prediction has garnered significant recognition as a pivotal component in realizing successful early warnings and implementing effective control measures. This task remains challenging as landslide deformation involves not only temporal dependency within time series data but also spatial dependence across various regions within landslides. The present study proposes a landslide spatiotemporal displacement forecasting model by introducing attention-based deep learning algorithms based on spatiotemporal analysis. The Maximal Information Coefficient (MIC) approach is employed to quantify the spatial and temporal correlations within the daily data of Global Navigation Satellite System (GNSS) observations. Based on the quantitative spatiotemporal analysis, the proposed prediction model combines a convolutional neural network (CNN) and long short-term memory (LSTM) network to capture spatial and temporal dependencies individually. Spatial–temporal attention mechanisms are implemented to optimize the model. Additionally, we develop a single-point prediction model using LSTM and a multiple-point prediction model using the CNN-LSTM without an attention mechanism to compare the forecasting capabilities of the attention-based CNN-LSTM model. The Outang landslide in the Three Gorges Reservoir Area (TGRA), characterized by a large and active landslide equipped with an advanced monitoring system, is taken as a studied case. The temporal MIC results shed light on the response times of monitored daily displacement to external factors, showing a lagging duration of between 10 and 50 days. The spatial MIC results indicate mutual influence among different locations within the landslide, particularly in the case of nearby sites experiencing significant deformation. The attention-based CNN-LSTM model demonstrates an impressive predictive performance across six monitoring stations within the Outang landslide area. Notably, it achieves a remarkable maximum coefficient of determination (R²) value of 0.9989, accompanied by minimum values for root mean squared error (RMSE), absolute mean error (MAE), and mean absolute percentage error (MAPE), specifically, 1.18 mm, 0.99 mm, and 0.33%, respectively. The proposed model excels in predicting displacements at all six monitoring points, whereas other models demonstrate strong performance at specific individual stations but lack consistent performance across all stations. This study, involving quantitative deformation characteristics analysis and spatiotemporal displacement prediction, holds promising potential for a more profound understanding of landslide evolution and a significant contribution to reducing landslide risk.

Many landslides are triggered by excess precipitation. In the eastern part of China, landslides caused by extreme rainfall from typhoons in the monsoon season are the main geomorphological process with catastrophic impacts on society and the environment. In this study, Wenzhou City in eastern China was taken as the study area, and we compiled a detailed inventory of rainfall-triggered landslides between 1999 and 2016. The developmental characteristics of these landslides were determined with an emphasis on temporo-spatial distribution. The results showed that most of the landslides were located in the mountainous area of the western part of Wenzhou City. Landslides triggered by typhoon rainfall were commonly concentrated in a short period from July to September, when more than 70% of the landslides occurred. The landslides in this region were mainly of the debris-flow type, most of which were on a small scale, but had severe effects because of large elevation differences and long runout distances. Because the precipitation in typhoon events was commonly extreme, the initiation area of most landslides coincided with the region of highest hourly precipitation. Our results can provide reference data and guidelines for developing an early warning system for landslides and risk reduction in the study area.

Landslides triggered by extreme rainfall often cause severe casualties and property losses. Therefore, it is essential to accurately assess and predict building vulnerability under landslide scenarios for effective risk mitigation. This study proposed a quantitative framework for vulnerability assessments of structures. It integrated extreme rainfall analysis, landslide kinematic assessment, and the dynamic response of structures. The study area is located in the northern mountainous region of Tianjin, China. It lies within the Yanshan Mountains, serving as a key transportation corridor linking North and Northeast China. The Sentinel-1A satellite imagery consisting of 77 SLC scenes (from October 2014 to November 2023) identified a slow-moving landslide in the region by using the SBAS-InSAR technique. High-resolution topographic data of the slope were first acquired through UAV-based remote sensing. Next, historical rainfall data from 1980 to 2017 were analyzed. The Gumbel distribution was used to determine the return periods of extreme rainfall events. The potential slope failure range and kinematic processes of the landslide were then simulated by using numerical simulations. The dynamic responses of buildings impacted by the landslide were modeled by using ABAQUS. These simulations allowed for the estimation of building vulnerability and the generation of vulnerability maps. Results showed that increased rainfall intensity significantly enlarged the plastic zone within the slope. This raised the likelihood of landslide occurrence and led to more severe building damage. When the rainfall return period increased from 50 to 100 years, the number of damaged buildings rose by about 10%. The vulnerability of individual buildings increased by 10% to 15%. The maximum vulnerability value increased from 0.87 to 1.0. This model offers a valuable addition to current quantitative landslide risk assessment frameworks. It is especially suitable for areas where landslides have not yet occurred.