Classifying ground deformation processes, such as landslides, subsidence, deep-seated gravitational slope deformations (DSGSDs), and mining-induced deformations, is key for large-scale hazard assessment and national land use management. Earth observation provides heterogeneous data over the same geographic region, including Interferometric Synthetic Aperture Radar (InSAR) time series, multispectral imagery, and terrain products. However, effectively integrating such spatiotemporal information from multimodal datasets remains a major challenge. In order to fully utilize the rich information contained in the time series and to exploit the complementary strengths of spatial and temporal data, we propose a dual-branch deep learning approach that integrates InSAR ground deformation time series with geospatial information for classifying slow-moving ground deformation processes. To validate the approach, we construct a ground deformation dataset containing over 26,000 Active Deformation Areas (ADAs), labelled into four deformation types: Landslide, Subsidence, DSGSD, and Mining. Results demonstrate that our model achieves an overall classification accuracy exceeding 90% on both ascending and descending test dataset, though confusion remains between certain classes, such as landslides and DSGSD. Explainable AI (XAI) analysis indicates that spatial and morphological features contribute more significantly to classification performance than temporal deformation patterns, with clearer distinctions for subsidence and mining, but more overlap between landslides and DSGSDs. This work highlights the strength of multi modal data fusion method to classify ground deformation processes, while setting the stage for future research.

Heavy rainfall and earthquake in mountain areas usually trigger numerous landslides. Fast and accurate mapping of landslides is crucial for risk management and emergency rescue. Deep learning-based landslide detection methods can automate identification, but convolutional neural network (CNN) models focus primarily on local features, often missing crucial global context in landslide images. Conversely, Transformer-based models excel at capturing global features but are hindered by high computational complexity. As a result, existing detection models struggle to strike an effective balance between accuracy and efficiency. To address this issue, this article presents a lightweight landslide detection method based on the newly proposed Mamba network. Specifically, a landslide detection model named SegMamba2D with an encoder–decoder structure is proposed. In the encoder, the Mamba network is used to extract multiscale features. A state-space model (SSM) is employed to reduce computational complexity while maintaining accuracy. In the decoder, a multilayer perceptron is used to build a lightweight decoder, ensuring that the model’s overall complexity remains low. The experimental results on both public and new datasets demonstrate that SegMamba2D achieves a superior landslide detection accuracy, with an approximately 2% improvement in$F1$score across various scenarios over conventional models, while significantly reducing computational costs. Additionally, SegMamba2D demonstrates robust generalization performance across diverse research areas. These advancements highlight the model’s potential to enhance accuracy in creating landslide inventories and expedite emergency response times during landslide disasters. The source code is available athttps://github.com/xiaochuan-tang/SegMamba2D

Landslide hazards pose a great threat to the local residents and infrastructure in mountain areas. Numerous technologies have been invented to monitor landslides, and large amounts of high-resolution spatio-temporal data are consistently emerging. These data are highly related to the national security. The local governments release legislation to regulate the sharing of these data. However, the existing landslide detection models explicitly or implicitly assume that landslide monitoring and mapping data are directly shared in a centralized server. There is a gap between landslide detection models and landslide data sharing. To bridge this gap, this letter proposes a privacy-preserving machine learning method named federated learning-based landslide detection (FedLD) for landslide detection. First, horizontal federated learning (HFL) is introduced to protect the data privacy of the modeling process of landslide detection, enabling the development of landslide detection models without direct sharing of the original landslide monitoring data. Second, a new marginal contribution (MC) metric is proposed to measure the contribution of the participants of federated landslide detection models and is used to develop a model aggregation algorithm for federated landslide detection. Experimental results demonstrated that FedLD is able to protect the privacy of popular deep learning-based landslide detection models and achieves competitive landslide classification performance. Therefore, federated learning (FL) provides an effective solution for promoting data sharing in landslide detection.

In this letter, we propose a Deep Learning (DL) based approach which exploits multispectral Sentinel-2 open-source data and a small-size inventory to map artisanal and small-scale mines (ASM). The study area is in central northern Burkina Faso (Africa) and is characterized by a semi-desert environment that makes mapping challenging. In sub-Saharan Africa, artisanal and small-scale mining represents a source of subsistence for a significant number of individuals. However, because ASM are often illegal and uncontrolled, the materials employed in the excavation process are highly dangerous for the environment as well as for the lives of the people involved in the mining activities. One of the most important aspects regarding ASM is the record of their spatial location which, at the moment, is missing in most of the African regions. Performance evaluation of two state-of-art DL architectures (U-Net, and Attention Deep Supervised Multi-Scale U-Net - ADSMS U-Net) is provided, along with an in-depth analysis of the predictions when dealing with both dry and rainy seasons. The ADSMS U-Net architecture yields generally more accurate predictions than the basic U-Net allowing us to better discriminate ASM in such an environment. The findings show that the proposed approach can detect ASM in semi-desertic areas starting with a few samples at a low cost in terms of both human and financial resources.

In this letter, we use deep learning convolutional neural networks (CNNs) to compare the landslide mapping and classification performances of optical images (from Sentinel-2) and synthetic aperture radar (SAR) images (from Sentinel-1). The training, validation, and test zones used to independently evaluate the performance of the CNN on different datasets are located in the eastern Iburi subprefecture in Hokkaido, where, at 03.08 local time (JST) on September 6, 2018, an Mw 6.6 earthquake triggered about 8000 coseismic landslides. We analyzed the conditions before and after the earthquake exploiting multipolarization SAR as well as optical data by means of a CNN implemented in TensorFlow that points out the locations where the landslide class is predicted as more likely. As expected, the CNN runs on optical images proved itself excellent for the landslide detection task, achieving an overall accuracy of 98.96%, while CNNs based on the combination of ground range detected (GRD) SAR data reached overall accuracies beyond 95%. Our findings show that the integrated use of SAR data may also allow for rapid detection even during storms and under dense cloud cover and provides comparable accuracy to classical optical change detection in landslide recognition and detection.

This study describes the assessment of landslide susceptibility in Sicily (Italy) at a 1:100,000 scale using a multivariate logistic regression model. The model was implemented in a GIS environment by using the ArcSDM (Arc Spatial Data Modeller) module, modified to develop spatial prediction through regional data sets. A newly developed algorithm was used to automatically extract the detachment area from mapped landslide polygons. The following factors were selected as independent variables of the logistic regression model: slope gradient, lithology, land cover, a curve number derived index and a pluviometric anomaly index. The above-described configuration has been verified to be the best one among others employing from three to eight factors. All the regression coefficients and parameters were calculated using selected landslide training data sets. The results of the analysis were validated using an independent landslide data set. On an average, 82% of the area affected by instability and 79% of the not affected area were correctly classified by the model, which proved to be a useful tool for planners and decision-makers.

Interferometric SAR data are used to derive morphometric terrain attributes required by geomorphological and hydrogeological applications. Instead of generating an interferometric Digital Terrain Model (DTM) and subsequently derive the terrain attributes, we compute these quantities directly from the interferogram. Experiments demonstrate that, when compared with traditional DTM-based measures, SAR based attributes seem more stable and offer best performances. Results shown in this paper have been obtained by processing ERS-1/2 SAR data referring to a typical Alpine mountain basin.