Daniel S Adams

Bio

Daniel is an R&D Data Scientist at Oak Ridge National Laboratory, where he develops high-resolution models of human populations and the built environment at global scales. His work integrates ecological theory, human geography, and machine learning to represent how people inhabit and move through landscapes.

He leads the advancement of GeoAI methods that incorporate spatial structure, behavioral dynamics, and uncertainty, shifting population modeling from correlation-driven prediction toward theory-grounded representation of human–environment systems. Prior to joining ORNL, Daniel worked with the U.S. Fish and Wildlife Service, applying geo-statistical modeling to conservation and landscape planning.

His broader research program investigates how principles from population ecology and complex systems can guide statistical learning approaches for human settlement patterns, migration pathways, and exposure risk in data-limited settings.

Daniel earned his B.S. in Geosciences (GIS), M.S. in Informatics, and Ph.D. in Environmental Science with a research concentration in GeoAI from Tennessee Technological University, where his doctoral work focused on theory-informed population modeling and spatial machine learning.

Publications