Work

Causal Links: Land Cover Change, Climate, and Policy Shocks

Year: 2026
Type: other
Abstract: This short paper presents LandShift’s approach to investigating the causal relationships between land cover change, climate pressures, and policy interventions across European landscapes. It focuses on integrating Earth Observation data, climate indicators, extreme event descriptors, and policy information through Causal Machine Learning techniques. The paper also describes how Average Treatment Effect (ATE) and Conditional Average Treatment Effect (CATE) estimates can be used to assess the impacts of climate and policy shocks, highlighting spatial differences and supporting evidence-based, climate-resilient land-use management strategies.
Language: English
Open Access status: green
OpenAlex ID: W7224658427
Cites:
Cited by:
Related to: 10