Welcome! I’m Daniel Feldmeyer, a researcher working at the intersection of AI, spatial statistics, and uncertainty.

I develop interpretable models for geospatial data — quantifying error, stress-testing decisions, and translating insights into policy and practice.

My background combines a Ph.D. in Spatial Planning with postdoctoral research at Princeton University.

Research Focus

  • Spatial AI — designing models that integrate spatial structure and context

  • Uncertainty Quantification — understanding and communicating error in complex systems

  • Policy Design — connecting data-driven insights with decision-making and equity outcomes

  • Interpretability — making AI models transparent, reproducible, and trustworthy

Current Work

At Princeton, I explore how uncertainty shapes the reliability of social and environmental indicators — and how more interpretable models can support equitable policy.

This includes:

  • Developing spatially explicit neural networks with built-in interpretability

  • Modeling uncertainty propagation in composite indicators and risk indices

  • Evaluating how uncertainty affects policy thresholds and designation decisions

Looking Ahead

While rooted in academic research, I’m interested in applied AI — bridging science, design, and decision-making.

I am always happy to discuss ideas and prospects, where data-driven tools can make complex systems more transparent and actionable — from climate risk to social resilience and spatial analytics.

Education & Background

  • Postdoctoral Research Associate, Princeton University

  • Ph.D. in Spatial Planning, University of Stuttgart (magna cum laude)

  • Dipl.-Ing. & M.Na.R.M.&E.E., BOKU Vienna & Lincoln University, New Zealand