I am a computational data scientist working on geospatial AI and AI for science. In 2023 I proposed autonomous GIS: AI agents that find geospatial data, run spatial analysis, and make maps from plain-language requests. I build these agents, including LLM-Geo, LLM-Find, and GIS Copilot.
I also apply spatial data and machine learning to public health and cities, from hourly population estimates for U.S. neighborhoods to mosquito habitat prediction for malaria control. Before research, I spent more than ten years in the geospatial industry as an engineer, developer, manager, and chief technology officer.
A warehouse of research knowledge built from the paper corpus. Every paper becomes a case, and the theories, data, models, math, tools, evaluation metrics, and reasoning patterns emerge from mining the cases, so that researchers, mainly AI, can stand on the shoulders of giants.
An experimental framework that represents how parts of a system influence one another, so that people and scientific AI tools can use the same computer model to test changes and compare outcomes.
Everyday metaphors (a rotor, a brake, a factory and warehouse, recycling pumps, and balance scales) that turn the brain's dopamine pathway into a machine students can watch, plus a driving game, to help students better understand the complicated addiction mechanism.
A research graph with the same form at every scale, built from standardized research units, so that AI agent swarms and human experts can grow scientific knowledge together.
arXiv preprint arXiv:2504.01170 (2025)DOI
Annals of GIS (2025)DOI
International Journal of Digital Earth 18(1), 2497489 (2025)
International Journal of Digital Earth 18(1), 2458688 (2025)DOI
