Detecting rainfall-induced landslides with Sentinel-1 SAR: Evidence from the Andes

Detection of extreme rainfall-induced landslides in mountainous areas using ensemble machine learning and Sentinel-2 satellite image analysis

Landslide detection is a fundamental prerequisite for subsequent investigations, including landslide susceptibility mapping and landslide risk assessment. In mountainous regions with complex terrain conditions, this task is particularly challenging due to the limited accessibility of landslide sites for direct field investigation and data acquisition. Recent advances in remote sensing image analysis have enabled efficient detection and extraction of landslide information through the analysis of changes in land cover and topographic characteristics derived from pre- and post-event imagery. Nevertheless, the application of remote sensing techniques still faces several limitations, particularly in discriminating actual landslide areas from vegetation loss caused by anthropogenic activities such as deforestation and infrastructure construction. To overcome these limitations, this study applied ensemble machine learning approaches using satellite imagery acquired from the Sentinel-2 satellite to detect landslide locations. Pre- and post-event satellite images associated with the extreme rainfall-induced landslide events that occurred in late October 2020 in the mountainous region of Phuoc Son were collected and analyzed. In addition to satellite imagery, several conditioning factors, including slope and rainfall, were incorporated into the models to minimize the misclassification of non-landslide areas as landslides. The training and validation results obtained from three models, namely Logistic Regression, Random Forest, and XGBoost (eXtreme Gradient Boosting), demonstrated excellent predictive capability for all models. Among them, the XGBoost model achieved the highest predictive performance, with an AUC value of 0.999 on the validation dataset. Subsequently, the XGBoost model was employed to identify landslide locations across the entire study area. Validation based on field survey data and Google Earth imagery further confirmed the high effectiveness and reliability of the proposed approach.

Monitoring Radar Backscatter Changes Associated with Potential Land Subsidence in Herat City Using Sentinel-1 Images

SAR-Based Flood Detection and Agricultural Land Cover Vulnerability in the Loukkos Floodplain: Implications for Land Use Management in Larache Province, Morocco

Flood events in agricultural floodplains reflect not only rainfall intensity but the vulnerability of the affected area at the moment of the event. This study examines the January–February 2026 flood in Larache Province, Morocco, through an integrated remote sensing workflow combining Sentinel-1 SAR, CHIRPS precipitation, and Dynamic World land cover in Google Earth Engine, processed via the rgee R package. Flood extent was mapped using SAR backscatter change detection and cross-checked against rainfall dynamics, yielding about 6660 ha of inundation (2.4% of the province), concentrated along the main Loukkos river corridor and adjacent floodplain around Ksar El Kebir, with smaller scattered patches to the south. Land cover was assessed across four temporal windows (spring 2025, pre-event, post-event, and spring 2026) to evaluate how the landscape entered the event and how it recovered. A significant share of normally cultivated land was in a bare-soil state before the flood, a condition that the literature associates with increased runoff. Post-flood analysis across 25 sample areas grouped into three geomorphic zones shows spatially uneven recovery, with cropland still below seasonal norms in spring 2026. These patterns are consistent with structural land-use conditions (wetland loss, intensive seasonal agriculture, drought-degraded soils) that may have amplified an already severe event. The findings support cover cropping, updated flood-hazard zoning, and targeted wetland restoration to reduce vulnerability in the Loukkos floodplain and comparable Mediterranean alluvial floodplains.

Erosion induced coastal changes in Karasu, Türkiye: new evidence from GNSS and remote sensing data

Coastal regions are highly sensitive to both natural processes and anthropogenic pressures including settlement, tourism, industry, and transportation, in addition to the impacts of climate change. Continuous monitoring of these areas is therefore essential for sustainable coastal management and for enabling rapid response to potential erosion hazards. Such changes can be effectively monitored using geodetic and remote sensing techniques. The study area is located in the Karasu district of Sakarya Province, in the northwestern part of Türkiye, where significant coastal erosion has been observed. Erosion mitigation measures were initiated in 2010 following the identification of the problem. Since then, the shoreline has retreated approximately 100 m landward, although the construction of breakwaters has partially reduced the erosion rate. In this study, the current state of coastal change was investigated using open-access Sentinel-2 and Sentinel-1 datasets. The Normalized Difference Water Index (NDWI) was applied to optical imagery, while backscatter information derived from Synthetic Aperture Radar (SAR) data was used to delineate the land–water boundary. Additionally, shoreline data obtained from Global Navigation Satellite System (GNSS) observations were adopted as reference data for accuracy assessment. Based on GNSS surveys conducted at two-year intervals within the same period, an erosion area of 12,069 m² and an accretion area of 77,410 m² were quantified along an approximately 9 km coastal segment. The results indicate that shoreline extraction from Sentinel-2 imagery shows significantly higher consistency with GNSS-derived reference data compared to Sentinel-1 results. Overall, Sentinel-2 data provide more reliable and accurate shoreline delineation, suggesting that they are highly suitable for rapid and effective coastal erosion monitoring in support of sustainable coastal management.

Detection and analysis of cyclonic events through satellite-based remote sensing techniques for coastal areas of Pakistan

This study reviews the unusual lifecycle and reach of Cyclone Asna (August–September 2024) over the North Arabian Sea with special focus on its inland re-intensification after landfall, a behavior not typically seen in that region. Remote sensing satellite platforms combined with geographic information systems (GIS) allow a multi-parameter assessment of Asna's track, rain patterns, flood extents, and resulting damage across Pakistan's coastal belt and deeper inland areas. Sentinel's 2 NDWI images map surface water changes before and after the storm, while integrated IMERG rainfall estimates and time-stamped damage reports identify high-risk areas and illuminate the cyclone's social and economic costs. Karachi and adjacent coastal towns recorded isolated totals above 266 mm, sparking extensive urban floods, power outages, and collapse of key transport links, all driven by Asna's slow forward motion and prolonged onshore presence. Asna's inland intensification was caused by a rare overlap of monsoon moisture feeding in from both the Arabian Sea and Bay of Bengal, upper-level divergence, saturated soils, high surface heat flux, and persistent mid- to upper-level cyclonic vorticity factors that together sustained the storm's vertical structure far beyond normal landfall limits. Broadly speaking, both the warmer Arabian Sea and its greater moisture-holding capacity are driving a recent increase in hybrid cyclone systems across the region. This study confirms that trend and points to satellite monitoring as an invaluable tool for bettering disaster preparedness and adaptive planning. As the case of cyclone Asna shows, predictive models and urban resilience plans must now be revised to reflect unusual cyclone behavior strengthened by evolving climate dynamics.

Landslides and vegetation fragmentation drive hydro-sedimentary hazards and urban flooding in Uvira

Across the mountainous regions of the East African Rift, interactions between human activities and extreme rainfall events can intensify urban hydro-geomorphological hazards. Yet, observation remains challenging, as remote sensing in humid tropical terrains can be constrained by e.g., persistent cloud cover and dense canopy. This study focused on Uvira (Democratic Republic of the Congo), a city built on narrow alluvial fans along Lake Tanganyika’s northwestern shores, where recent rainfall events (2020-2021) culminated in severe floods. We examined the upstream-downstream sediment cascade to clarify the processes driving flood genesis. We applied an integrated approach combining extensive field observation campaigns, morpho-dimensional classification of 225 erosive events, Sentinel-2 imagery processed via Google Earth Engine, and statistical workflow. Results revealed a predominance of landslides (44.40%) and sheet erosion (38.20%), largely influenced by steep gradients between 900 and 1700 m. Statistical analysis (χ2 = 35.42; p > 0.05) showed no significant link between land-cover class and slope failures, suggesting that fragmented vegetation cover, likely linked to unplanned urbanization, may drive localized infiltration and slope instability. Hazards appeared controlled by dual rainfall regimes: seasonal accumulation (800-1000 mm) followed by short, intense pulses (e.g., 114 mm in 6 h). These conditions generated rapid hydro-sedimentary responses, with 3-4 m riverbed aggradation at the Kavimvira and Mulongwe River’s outlets, severely affecting downstream residential areas. Conversely, the Kalimabenge River carried a smaller sediment load, likely reflecting upstream reforestation. This work advances understanding of sediment connectivity and vegetation fragmentation in tropical rift environments. It highlights the need to move beyond curative dredging toward integrated watershed management, eco-protective measures, and participatory monitoring. Given the scarcity of hydrometeorological data in Uvira, these findings provide a baseline for land-use planning and risk reduction.