Nathan Kleist, PhD

Nathan Kleist works in close collaboration with the Bureau of Land Management and other partners to co-produce novel approaches that harness remotely sensed data and artificial intelligence (AI), including machine learning, in land-management science to support efficient, defensible stewardship of America's working rangelands. Nathan develops predictive machine-learning models that integrate drought, soil, vegetation, and agency monitoring data to map land-health outcomes, delivering scalable, data-driven tools that support grazing permit evaluations and multiple-use land management. His work emphasizes transparent, reproducible methods and rigorous model development that strengthen the defensibility of science used in permitting decisions. Nathan plays a leading role in developing a growing body of literature syntheses and streamlined science-delivery techniques and products for resource- and land-management questions. He also brings a strong background in wildlife research, including several influential studies on birds from the oil and gas fields of northwestern New Mexico, as well as mule deer habitat modeling to support healthy big-game populations. He leads work with the Federal Highway Administration on an interagency synthesis of wildlife-crossing science, contributing to wildlife-vehicle conflict mitigation that informs infrastructure planning to improve transportation safety while protecting economically important wildlife.