Against the backdrop of global warming and increased rainfall, the hazards and potential risks of landslides are increasing. The rapid generation of a landslide inventory is of great significance for landslide disaster prevention and reduction. Deep learning has been widely applied in landslide identification due to its advantages in terms of its deeper model structure, high efficiency, and high accuracy. This article first provides an overview of deep learning technology and its basic principles, as well as the current status of landslide remote sensing databases. Then, classic landslide deep learning recognition models such as AlexNet, ResNet, YOLO, Mask R-CNN, U-Net, Transformer, EfficientNet, DeeplabV3+ and PSPNet were introduced, and the advantages and limitations of each model were extensively analyzed. Finally, the current constraints of deep learning in landslide identification were summarized, and the development direction of deep learning in landslide identification was analyzed. The purpose of this article is to promote the in-depth development of landslide identification research in order to provide academic references for the prevention and mitigation of landslide disasters and post-disaster rescue work. The research results indicate that deep learning methods have the characteristics of high efficiency and accuracy in automatic landslide recognition, and more attention should be paid to the development of emerging deep learning models in landslide recognition in the future.

Multi-temporal Interferometric Synthetic Aperture Radar technique (MTInSAR) has emerged as a valuable tool for measuring ground motion in a wide area. However, interpreting displacement time series and identifying dangerous signals from millions of InSAR coherent targets is challenging. In this study, we propose a method combining stacked autoencoder (SAE) and convolutional neural network (CNN) to classify InSAR time series and ease the interpretation of movements. The InSAR time series are classified into five categories, including stable, linear, accelerating, deceleration, and phase unwrapping error (PUE). The accuracy of labeled samples reaches 95.1%, reflecting the performance of the proposed method. This method was applied to the InSAR results for Kunming extracted from 171 ascending Sentinel-1 images from January 2017 to September 2022. The classification map of the InSAR time series shows that stable coherent points dominate around 79.28% of the area, with linear patterns at 10.70%, decelerating at 5.30%, accelerating at 4.72%, and PUE patterns at 3.60%. The results demonstrate that this method can distinguish different ground motion features and detect nonlinear deformation signals on a large scale without human intervention.

As a city undergoes large-scale construction and expansion, there is an urgent need to monitor the stability of the ground and infrastructure. The time-series InSAR technique is an effective tool for measuring surface displacements. However, interpreting these displacements in a built environment, where observed displacements consist of mixed signals, poses a challenge. This study uses principal component analysis (PCA) and the k-means clustering method for exploring deformation series within an unsupervised learning context. The PCA method extracts the dominant components in deformation series, whereas the clustering method identifies similar deformation series. This method was tested on Kunming City (KMC) using C-band Sentinel-1, X-band TerraSAR-X, and L-band ALOS-2 PALSAR-2 data acquired between 2017 to 2022. The experiment demonstrated that the suggested unsupervised learning approach can group PS points with similar kinematic characteristics. Five types of deformation kinematic characteristics were discovered in the three SAR datasets: upward, slight upward, stability, slight downward, and downward. According to the results, less than 20% of points exhibit significant motion trends, whereas 50% show small velocity values but still demonstrate movement trends. The remaining 30% are relatively stable. Similar clustering results were obtained from the three datasets using unsupervised methods, highlighting the effectiveness of identifying spatial–temporal patterns over the study area. Moreover, It was found that clustering based on kinematic characteristics enhances the interpretation of InSAR deformation, particularly for points with small deformation velocities. Finally, the significance of PCA decomposition in interpreting InSAR deformation was discussed, as it can better represent series with noise, enabling their accurate identification.

Developing landslide susceptibility modeling is essential for detecting landslide-prone areas. Recently, deep learning theories and methods have been investigated in landslide modeling. However, their generalization is hindered because of the limited size of landslide data. In the present study, a novel deep learning-based landslide susceptibility assessment method named deep random neural network (DRNN) is proposed. In DRNN, a random mechanism is constructed to drop network layers and nodes randomly during landslide modeling. We take the Lushui area (Southwest China) as the case and select 12 landslide conditioning factors to perform landslide modeling. The performance evaluation results show that our method achieves desirable generalization performance (Kappa = 0.829) and outperforms other network models such as the convolution neural network (Kappa = 0.767), deep feedforward neural network (Kappa = 0.731), and Adaboost-based artificial neural network (Kappa = 0.732). Moreover, the robustness test shows the advantage of our DRNN, which is insensitive to variations in training data size. Our method yields an accuracy higher than 85% when the training data size stands at only 10%. The results demonstrate the effectiveness of the proposed landslide modeling method in enhancing generalization. The proposed DRNN produces accurate results in terms of delineating landslide-prone areas and shows promising applications.

Traditional hazard assessment often relies on simple spatial overlays of static susceptibility and dynamic rainfall thresholds, ignoring the spatial heterogeneity of geological responses to rainfall. To address this limitation, this study proposes a meteorological hazard assessment and dynamic early warning framework for Nujiang Prefecture, Yunnan Province, driven by heuristic spatial heterogeneity weighting. Specifically, this study introduces an S-T-C (Susceptibility–Rainfall trigger index–Causal-heuristic modulation factor) coupling framework that employs Causal Forest Double Machine Learning (CF-DML) to approximate conditional rainfall–geohazard associations and integrates them with static susceptibility and dynamic rainfall threshold modeling for warning zoning. The framework combines an antecedent effective rainfall threshold model (Antecedent Effective Rainfall Intensity–Duration–Daily Rainfall, EI-D-R) with an AutoGluon-based susceptibility model (AUC = 0.9178), and uses CF-DML as a flexible non-linear estimator to approximate conditional responses modulated by environmental factors. This heuristic adjustment is then incorporated into the S-T-C coupling framework. A retrospective case application shows that at the same observed Probability of Detection (POD = 76.5%), the S-T-C framework produces a more spatially selective warning footprint compared to traditional S-T product coupling, with very low-hazard zones expanding from 32.67% to 70.64% (a relative increase of 116.19%). Rather than claiming validated causal identification, this work illustrates that using CF-DML as an association-based, heuristic spatial-heterogeneity weighting approach can provide a more spatially explicit and retrospectively evaluated basis for geohazard assessment and regional risk management, subject to the data and modeling limitations discussed.

Landslide deformation monitoring plays a critical role in geohazard prevention and risk mitigation in mountainous regions, where timely and reliable deformation information is essential for early warning and disaster management. Monitoring landslide deformation in mountainous areas remains a persistent challenge, largely due to rugged topography, dense vegetation cover, and low interferometric coherence—factors that substantially limit the effectiveness of conventional InSAR methods. To address these issues, this study aims to develop a robust time-series InSAR framework for enhancing deformation detection and measurement density under low-coherence conditions in complex mountainous terrain, and accordingly introduces the Sequential Estimation and Total Power-Enhanced Expectation–Maximization Inversion (SETP-EMI) approach, which integrates dual-polarization Sentinel-1 SAR time series within a recursive estimation framework, augmented by polarimetric coherence optimization. This methodology allows for dynamic assimilation of SAR data, improves phase quality under low-coherence conditions, and enhances the extraction of distributed scatterers (DS). When applied to Zhenxiong County, Yunnan Province—a region prone to geohazards with complex terrain—the SETP-EMI method achieved a landslide detection rate of 94.1%. It also generated approximately 2.49 million measurement points, surpassing PS-InSAR and SBAS-InSAR results by factors of 22.5 and 3.2, respectively. Validation against ground-based leveling data confirmed the method’s high accuracy and robustness, yielding a standard deviation of 5.21 mm/year. This study demonstrates that the SETP-EMI method, integrated within a DS-InSAR framework, effectively overcomes coherence loss in densely vegetated plateau regions, improving landslide monitoring and early-warning capabilities in complex mountainous terrain.