A MACHINE LEARNING APPROACH TO LANDSLIDE SUSCEPTIBILITY MAPPING IN THE BLUE RIDGE MOUNTAINS OF NORTH CAROLINA

Landslides pose significant hazards to human safety, infrastructure, and the environment, particularly in regions of high elevation that experience extended periods of heavy rainfall. The Blue Ridge Mountains, a physiographic province of North Carolina, are known for their steep hillslopes and high susceptibility to landsliding, especially during heavy rainfall events such as the recent hurricane Helene in late September of 2024. This study aims to develop a landslide susceptibility map for the Blue Ridge Mountains using the Random Forest (RF) machine learning algorithm. The RF model is trained using a dataset that combines landslide inventory data with several input variables, including high-resolution LiDAR-derived topographic characteristics, lithologic conditions, anthropogenic influence, and climatic factors — all known to increase landslide occurrence. The results are expected to indicate the relative importance of key factors influencing landslide susceptibility in the Blue Ridge Mountain region, as well as provide a susceptibility map that offers a spatially explicit assessment of landslide risk across the study area. This map can serve as a valuable tool for land use planning, disaster preparedness, and risk mitigation efforts in the Blue Ridge region