This course provides a survey of the rapidly growing field of machine learning in the physical sciences. It covers various areas such as inverse problems, emulating physical processes, model discovery given data, and solution discovery given equations. It both introduces the background knowledge required to implement physics-informed deep learning and provides practical in-class coding exercises. Students have the opportunity to apply this emerging methodology to their own research interests across all fields of the physical sciences, including geophysics, climate, fluids, or other systems where the same technique applies. Recommended Prerequisite: Calculus (e.g. Math CME 21), Differential Equations (e.g. MATH 53 or PHYSICS CME 111) or equivalents. CME 215 is only open to graduate students. Undergraduate students should enroll in GEOPHYS CME 148 to satisfy WAYS requirements.
3 units · Letter or Credit/No Credit
This course provides a survey of the rapidly growing field of machine learning in the physical sciences. It covers various areas such as inverse problems, emulating physical processes, model discovery given data, and solution discovery given equations. It both introduces the background knowledge required to implement physics-informed deep learning and provides practical in-class coding exercises. Students have the opportunity to apply this emerging methodology to their own research interests across all fields of the physical sciences, including geophysics, climate, fluids, or other systems where the same technique applies. Recommended Prerequisite: Calculus (e.g. Math 21), Differential Equations (e.g. MATH 53 or PHYSICS 111) or equivalents. CME 215 is only open to graduate students. Undergraduate students should enroll in GEOPHYS 148 to satisfy WAYS requirements.
Offered in Spring 2027 at Stanford University.