High-Stakes Decisions from Low-Quality Data: AI for Biodiversity Decisions

The proliferation of big data has rapidly advanced global-scale monitoring of ecosystems and biodiversity. However, these advances in measuring species distributions and changing land cover are often followed by traditional decision-making processes that are reactive and heuristic-based. This talk will explore opportunities to leverage AI for not just monitoring nature, but also for making decisions — to design effective, timely interventions under resource constraints. I’ll present technical advances in machine learning, reinforcement learning, and causal inference, addressing research questions that emerged from on-the-ground challenges in wildlife conservation. Such interventions are the underpinnings of resource allocation, adaptive management, payment design, and other critical solutions for nature. I’ll also discuss ongoing work on invasive species management and optimizing biodiversity monitoring.

About the speaker:

Lily Xu is a Sun-Wu Assistant Professor at Columbia in the Department of Industrial Engineering and Operations Research. Her research develops AI methods across machine learning, optimization, and causal inference for planetary health challenges, with a focus on biodiversity conservation. Her work provides novel algorithms to enable practitioners to make effective decisions in the face of limited data, taking actions that are robust to uncertainty, effective at scale, and future-looking. She partners closely with NGOs and interdisciplinary researchers to bridge research and practice. Lily holds a PhD in computer science from Harvard University and was a postdoctoral research fellow at the University of Oxford with the Leverhulme Centre for Nature Recovery.

Time: 12:00 pm EST

Free!

Registration