Flood and landslide susceptibility assessment and multi hazard interaction mapping using machine learning and GIS for sustainable settlement planning in Nepal

The paper presents machine learning and GIS-based approach to map nationwide susceptibility to floods, landslides, and identify their potential interaction zones, and delineate critical multi-hazard flow zones through spatial adjacency analysis to identify four spatial zonation (low hazard zone, flood only zone, landslide only zone and their interaction zone). The interaction zone with multi-hazard flows represents susceptibility-based spatial connectivity rather than physically simulated cascading process.

The results showed that 19% of Nepal’s lowlands are medium to very highly susceptible to flood inundation, threatening approximately 900,000 people and over 3.4 million buildings; whilst in the hilly terrains, 40% is susceptible to slope-failure endangering 200,000 people and about 0.6 million buildings. Likewise, the critical multi-hazard flow zone covering 7,588 km² area that spatially connect corridors linking the interaction zones to downstream flood-prone populated areas, affects 88 km² built-ups and 1,722 km² cropland.

These findings are crucial for initial risk screening and use as decision support tool for risk-informed land use planning, derisk investments, and build resilient infrastructures to ensures safe shelters and settlements. I hope colleagues from SG1-DRR can advance this work by addressing the limitations in the paper and strengthen the understanding on complex risk-informed spatial planning for building resilient landscapes and economies.