About
This course is intended to provide students with a comprehensive overview of the rapidly-changing interface of glaciology with machine learning and artificial intelligence. Key topics that may be covered include
- An overview of machine learning methods for glaciologists
- Adjoint models and backpropagation
- Deep learning for glaciological remote sensing
- Gaussian process emulation for model prediction
- Deep learning-based emulation of ice physics
The course is primarily oriented towards researchers at all career stages that have strong foundational knowledge in glaciology, glaciological modeling, or remote sensing, and that wish to integrate ML methods into their work while simultaneously working to establish a community of practice.
The course will be held from July 4th - 13th, 2026 and will include 4 days of interactive lectures by course instructors, 3 days of student project development in collaboration with course instructors, a one day excursion to nearby Yellowstone National Park, and two days for travel and orientation. Previous instructors include
- Doug Brinkerhoff, University of Montana
- Ching-Yao Lai, Stanford University
- Mauro Perego, Sandia National Laboratory
- Daniel Cheng, NASA Jet Propulsion Laboratory
- Jacob Downs, University of Montana
Fixed costs for attending the course (including airfare, transportation, and room and board at the Taft-Nicholson Center) are covered by a generous grant from the National Science Foundation.