Quantifying uncertainty in landslide susceptibility mapping due to sampling randomness

The quality of landslide and non-landslide samples plays a crucial role in landslide susceptibility maps (LSMs) generated using machine learning algorithms. However, uncertainties arising from the collection of non-landslide samples can significantly compromise the reliability of these maps. Current methods, such as buffer-controlled sampling (BCS), often fail to address this issue adequately. This study aims to fill that gap by employing Monte Carlo simulations combined with BCS to quantify the uncertainties associated with non-landslide sampling and improve the accuracy of LSMs. A novel framework is proposed by incorporating landslide susceptibility confidence maps (LSCMs) to address the inherent uncertainty in BCS-based LSMs. The framework evaluates inconsistencies in LSMs, showing that maps generated by the same model may differ in over 30 % of the area due to variations in selection of non-landslide samples. The proposed approach outperforms traditional methods by correctly classifying landslide-prone areas, particularly in low and very low susceptibility zones, while providing a more reliable quantification of uncertainty. These findings underscore the limitations of traditional LSM methods and demonstrate that LSCMs offer a more robust tool for landslide hazard assessment. The framework enhances the precision of susceptibility mapping and provides critical insights for better risk mitigation and disaster preparedness.