Intersectional Risk Modeling & Mapping in Data Scarce Regions

This project develops a machine learning and data processing workflow for integrated risk modeling and mapping in data-scarce Low to Middle Income (LMI) countries, containing significant biodiversity prone to climate change. Using global datasets, the tool assesses risks by combining hazard model outputs with asset data, such as biodiversity intactness and human populations, to evaluate potential risk. Findings are validated through ground-truthing with local experts in targeted regions, including the greater San José metropolitan area, chosen for Costa Rica’s conservation focus and available high-quality data.