AI & Machine Learning Based Sustainability Policy

We develop AI- and data-driven methods to design, evaluate, and scale effective climate and conservation policies. Our research combines causal inference, behavioral economics, and machine learning to support evidence-based sustainability transitions. 

 Real-life applications of this research include:  

Conservation policy and impact evaluation: We study how incentives shape nature stewardship and evaluate how real-world conservation programs, such as forest protection and biodiversity policies, affect both environmental outcomes and local livelihoods. Our work provides robust evidence on what truly benefits both nature and people.

Evidence-based infrastructure: We develop data-driven tools and evidence syntheses that support transparent, real-time decision-making for policymakers and sustainability practitioners.