The lack of effective methods for rapid and accurate detection of landslide-damaged areas using satellite imagery and remote sensing data

The gap

Evidence profile

Sourced from the limitations and future-work section and stated research gap of the source papers, classified as general, drawn from work published between 2025 and 2026, spanning 6 journals. Those papers have been cited 16 times in total.

Supporting evidence — 8 representative gaps

• Remote sensing-based landslide prediction and risk assessment using a hybrid CNN–LSTM deep learning model (2026) · Scientific Reports · doi

  Despite its strong performance, several limitations should be noted. First, model accuracy depends on the quality and spatial resolution of remote sensing data, which may be affected by cloud cover, sensor noise, or DEM limitations. Second, the temporal component included only rainfall and reservoir-level fluctuations. The absence of additional time-series variables, such as soil moisture, ground deformation, or seismic activity, may limit representation of all triggering mechanisms. Third, the landslide inventory may be incomplete or biased toward Scientific Reports | (2026) 16:10687 | https://doi.org/10.1038/s41598-026-43927-5 14 www.nature.com/scientificreports/ Fig. 10. Landslide susceptibility maps provided based on deep learning: (a) CNN-only, (b) LSTM-only (the maps were generated using ArcGIS software version 4.10.1, Esri, https://www.esri.com/arcgis).‎ accessible areas, leading to higher uncertainty in regions with sparse records. The framework was evaluated only in Kerman Province, and its transferability to regions with different environmental conditions remains untested. In addition, statistical uncertainty analysis and repeated cross-validation were not performed; therefore, performance differences should be interpreted as indicative rather than statistically conclusive. Finally, random dataset splitting may introduce spatial autocorrelation between subsets, potentially resulting in optimistic estimates. Future studies should apply spatially independent validation strategies, test the framework in multiple regions, and incorporate additional spatiotemporal variables to enhance robustness and generalizability.

  generallimitationsevidence 5/5
  Keywords: regions performance limitations spatial additional variables landslide https maps arcgis esri uncertainty framework validation despite
• Understanding the role of lineament-controlled factors in landslide susceptibility: a machine learning approach in the Uhl Basin, Himachal Pradesh (2026) · Frontiers in Earth Science · doi

  Future studies can focus on the application of machine learning techniques for landslide susceptibility mapping in other regions. Future studies can investigate the use of other machine learning algorithms for landslide susceptibility mapping. Future studies can explore the integration of remote sensing data with machine learning techniques for landslide susceptibility mapping.

  generalfuture-work sectionevidence 5/5
  Keywords: future studies focus application machine learning techniques landslide
• Impact of extreme rainfall on triggering conditions and susceptibility for shallow landslides: a case study in the Alpes-Maritimes region (France) (2026) · Natural hazards and earth system sciences · doi

  The outputs and reliability of rainfall-duration thresholds and susceptibility maps can be strongly affected by the representativeness of the landslides included in the inventory. There is a need to investigate the impact of landslides triggered by extreme rainfall events on the determination of rainfall-duration thresholds and susceptibility maps.

  generalstated research gapevidence 5/5
  Keywords: outputs reliability rainfall-duration thresholds susceptibility maps strongly affected
• ChangeFormer-Based Detection of Landslide-Damaged Areas Using Sentinel-2 Imagery in South Korea (2026) · Land · doi

  The lack of effective methods for rapid and accurate detection of landslide-damaged areas using satellite imagery and remote sensing data. The need for a robust and generalizable model that can be applied to different regions and environments. The limited availability of reference data for landslide damage in some regions.

  generalstated research gapevidence 5/5
  Keywords: lack effective methods rapid accurate detection landslide-damaged areas
• GIS-based multi-criteria landslide susceptibility assessment in the Northwestern Himalaya, Jammu and Kashmir, India (2026) · Scientific Reports · doi

  Future research should focus on integrating high-resolution seismic datasets and multi-temporal environmental variables to develop dynamic landslide susceptibility models and improve hazard prediction accuracy. Machine learning models were not considered in the present study because they generally require large and balanced datasets with both presence and absence samples, extensive parameter tuning, and high computational resources, which were beyond the scope of this work.

  generallimitationsevidence 5/5
  Keywords: high datasets models future focus integrating resolution seismic multi temporal environmental variables develop dynamic landslide
• Landslide Susceptibility Mapping Using an LSTM Model with Feature-Selecting for the Yangtze River Basin in China (2025) · Water · cited 12× · doi

  The paper identifies a gap in existing landslide susceptibility mapping techniques, which may not effectively handle high-dimensional data. The study highlights the need for a framework that integrates feature selection techniques with sequence-based modeling. The paper notes that traditional machine learning algorithms and standard deep learning models may not perform well in landslide susceptibility mapping.

  generalstated research gapevidence 5/5
  Keywords: paper identifies gap existing landslide susceptibility mapping techniques
• Morphological characteristics and spatial distribution of shallow landslides in the Qinling-Daba Mountains, China (2026) · Frontiers in Earth Science · doi

  incorporate higher-resolution DEMs and multi-temporal remote sensing (including time-series vegetation indices and land cover products) to refine factor extraction and enable dynamic susceptibility assessment - use machine learning methods (e.g., random forest, artificial neural networks) to capture non-linear interactions among factors and improve predictive performance - conduct a multivariable presence-background analysis with spatial cross-validation to provide stronger evidence regarding the independent associations of environmental factors with landslide occurrence

  generalfuture-work sectionevidence 5/5
  Keywords: incorporate higher-resolution dems multi-temporal remote sensing including time-series
• Comparative Assessment of Quantitative Landslide Susceptibility Mapping Using Feature Selection Techniques (2026) · ISPRS International Journal of Geo-Information · cited 4× · doi

  Further research is needed to explore the application of feature selection techniques in landslide susceptibility mapping, - Additional experiments on different data splits are needed to confirm the stable performance of the models, - The study suggests examining how the distribution of each factor differs between landslide and non-landslide areas

  generalfuture-work sectionevidence 4/5
  Keywords: further research needed explore application feature selection techniques

Questions about this gap