Landslide Susceptibility Mapping of Urban Areas: Logistic Regression and Sensitivity Analysis applied to Quito, Ecuador

A novel approach to landslide susceptibility mapping in urban areas reveals that population and street/road density significantly enhance predictive accuracy, with the logistic regression model achieving a validation score of 0.79. This study highlights the importance of incorporating 'urban factors' into risk assessment models for Andean cities like Quito, Ecuador, where such data was previously underutilized. Sensitivity analyses demonstrated that fine-tuning model parameters could further improve prediction by up to 0.53%. The findings underscore the need for household-scale urban feature analysis to inform safer zoning and mitigate social and economic impacts of landslide risks in vulnerable regions.

Puente-Sotomayor, F., Mustafa, A., & Teller, J. (2021). Landslide Susceptibility Mapping of Urban Areas: Logistic Regression and Sensitivity Analysis applied to Quito, Ecuador. Geoenvironmental Disasters, 8(1). https://doi.org/10.1186/s40677-021-00184-0