Skip to main content


Holly Copeland

We created a probabilistic classification model using the nonparametric machine learning technique 'Random Forests' for oil and gas development potential from low (0) to high (1) across the western US. The six predictor variables used in the model were: geophysical data showing aeromagnetic, isostatic gravity, and Bouguer gravity anomalies, geology, topography and bedrock depth. Our binary response variable was geospatial point data on producing and non-producing oil and gas wells. Our estimates provide insights into the trajectory and eventual endpoint of oil and gas development, but the rate and exact location of development will be subject to additional factors not considered such as market demand, the capacity...
This is the data archive for the publication Ungulate Migrations of the Western United States, Volume 1 (Kauffman et al. 2020) and includes the collection of GIS map files that are mapped and described in the report. These map files are meant to provide a common spatial representation of the mapped migrations. This data release provides the means for ungulate migrations to be mapped and planned for across a wide variety of landscapes where they occur. Due to data sharing constraints of participating agencies, not all the files that underlie the mapped migrations included in the report have been released. Data can be viewed at: Data in this archive can be downloaded two ways. To download...
ScienceBase brings together the best information it can find about USGS researchers and offices to show connections to publications, projects, and data. We are still working to improve this process and information is by no means complete. If you don't see everything you know is associated with you, a colleague, or your office, please be patient while we work to connect the dots. Feel free to contact