Atmosphere Ocean Science Colloquium

Hybrid modeling: best of both worlds?

Speaker: Pierre Gentine, Columbia

Location: Warren Weaver Hall 1302

Date: Wednesday, April 1, 2020, 3:30 p.m.


In recent years, we have witnessed an explosion in the applications of machine learning, especially for environmental problems. Yet for broader use, those algorithms may need to respect exactly some physical constraints such as the conservation of mass and energy. In addition, environmental applications (e.g. drought impact) are typically focusing on extremes and on out-of-sample generalization rather than on the mean. This can be a problem for typical algorithms, which interpolate very well but have difficulties extrapolating. I will here show how a hybridization of machine learning algorithms, imposing physical constraints within them, can help tackle those different issues and offer a promising avenue for climate applications and process understanding.