Physics to Machine Learning and Machine Learning Back to Physics - A Warren Lecture

Pierre Gentine
Earth and Environmental Engineering & Earth and Environmental Sciences
Columbia University

ABSTRACT: Over the last couple of years, we have witnessed an explosion in the use of machine learning for Earth system science application ranging from Earth monitoring to modeling. Machine learning has shown tremendous success in emulating complex physics such as atmospheric convection or terrestrial carbon and water fluxes using satellite or high-fidelity simulations in a supervised framework. However, machine learning, especially deep learning, is opaque (the so-called black box issue) and thus a question remains: what (new) understanding have we really developed? 

I will here illustrate the value of lower dimensional, latent, representations to build new physical understanding of complex physical systems using machine learning. I will present several examples where machine learning and physics can advance together our understanding of complex physical systems and highlight the emergent behavior of the system. 

We will start with the example of  convective organization (i.e. the spatial organization of clouds) and their impact on precipitation, and will discuss new strategies for the terrestrial carbon and water cycles, where new physics can be learnt implicitly by building hybrid (machine learning+physics) models.  We will finally show next causal strategies going beyond standard correlations so that we can build more trustworthy and explainable algorithms. 

BIO: Pierre Gentine is the Maurice Ewing and J. Lamar Worzel professor of geophysics in the departments of Earth and Environmental Engineering and Earth and Environmental Sciences at Columbia University. He studies the terrestrial water and carbon cycles and their changes with climate change. Pierre Gentine is recipient of the National Science Foundation (NSF), NASA and Department of energy (DOE) early career awards, as well as the American Geophysical Union Global Environmental Changes Early Career, Macelwane medal and American Meteorological Society Meisinger award. He is the director of the new NSF Science and Technology Center (STC) for Learning the Earth with Artificial intelligence and Physics (LEAP), the largest funding mechanism of the NSF.