Summary
This paper presents a heuristic approach to landslide risk assessment in Guerrero State, Mexico, by integrating AutoML-derived susceptibility maps with ecological and socio-economic vulnerability assessments. Using freely available spatial data (remote sensing and official databases), the authors demonstrate that ecological vulnerability concentrates in mountainous zones whilst socio-economic vulnerability clusters around human settlements and infrastructure. The methodology is designed to be adaptable to other developing regions with limited resources and serves as a practical tool for landslide disaster prevention and regional management.
Regional applicability
Whilst this study focuses on Mexico's Guerrero State, the methodology's reliance on open-access spatial data and remote sensing makes it potentially transferable to United Kingdom upland and coastal regions vulnerable to landslides. However, direct application would require adaptation to UK administrative databases, land-use patterns, and settlement distributions; the approach's emphasis on developing-country constraints may have limited relevance to UK risk governance frameworks, which already employ established landslide susceptibility assessment protocols.
Key measures
Landslide susceptibility index, ecological vulnerability index, socio-economic vulnerability index, integrated landslide risk index
Outcomes reported
The study developed and applied a heuristic risk model integrating susceptibility maps (generated via AutoML) with vulnerability assessments (ecological and socio-economic) to landslide-prone areas in Guerrero State, Mexico. The integrated risk assessment mapped spatial variation in vulnerability and susceptibility, revealing distinct distributions between ecological and socio-economic vulnerability zones.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.