U.S. Geological Survey, Reston, VA, USA
Dr. Graham Lederer is a research geologist at the U.S. Geological Survey where he investigates the supply of mineral commodities critical for societal needs. His current projects focus on developing methods for mineral resource assessment and the application of machine learning techniques. Prior to the USGS, Graham earned a PhD at the University of California Santa Barbara while studying granites in Himalaya and was a post-doc at MIT.
Automated georeferencing and feature extraction of geological maps and mineral sites
In his keynote talk, he will present work conducted in partnership with the Defense Advanced Research Projects Agency (DARPA) on developing machine learning approaches for extracting data from map images. Two tasks that previously required time-intensive human effort, 1) georeferencing map images, and 2) legend-based feature extraction from map images, are discussed. Accurately locating and extracting the rich