U-Net Deep Learning for Geospatial Landslide Inventory Mapping in Genting Highlands, Malaysia

Genting Highland is predominantly the mode of landslides, especially prevalent during and post monsoon seasons. Globally, landslides encapsulates the widespread hydro-geological disaster elucidating their causes, risks, and impacts on infrastructure and human life. Attributed  from Malaysia natural undulated terrain, torrential rainfall, expanding urbanization contributed to the increasing landslide occurrences. Laying the groundwork for a more efficient landslide mapping over a vast area underscores the imperative need of Artificial Intelligence (AI). Landslide mapping to-date transitions from conventional delineation to employing U-Net, a deep learning architecture, to automate and expedite the process of identifying landslides from remote sensing data towards the emphasizes on rapid landslide mapping. This study is to create detailed landslide inventory maps by mapping new and old landslide footprint for Genting Highlands, with U-Net Deep Learning as a pivotal tool. Entail a systematic process, to identify landslide structures according to predefined categories, using high-resolution satellite imagery to train the U-Net model, and ultimately producing validated landslide maps for the region. The stages for integrating U-Net Deep Learning with geospatial analysis include data acquisition, pre-processing, DL training, analysis, and the final output of landslide mapping. Spot-7 imagery as input to the U-Net and  landslide semantic shapes that consist of crown, transportation body and foot, whereby pixel by pixel are classified when introduced. The anticipated results, showcasing the validity and precision of the model's landslide automated delineation on other imageries. Verification involves the comparison between U-Net's projected landslides to a manually delineated landslide inventory for Genting Highlands. Hence, this research provide precise and efficient tools for identifying and forecasting landslides in landslide-prone areas.