Dept. of Geosciences Colloquium: Physics-guided machine-learning for climate modeling
Janni Yuval, MIT
Global climate models represent small-scale processes, such as clouds and convection, using subgrid models known as parameterizations. Traditional parameterizations are usually based on simplified physical models, and inaccuracies in these parameterizations are a main cause for the large uncertainties in climate projections. Reducing these uncertainties is crucial since it will assist policymakers to plan proper adaptation and mitigation policies for climate change. Therefore, novel and computationally efficient approaches to subgrid parameterization development are urgently needed and are at the forefront of climate research. One alternative to traditional parameterizations is to use machine learning to learn new parameterizations which are data driven. However, machine-learning parameterizations might violate physical principles and often lead to instabilities when coupled to an atmospheric model. I will show how machine learning algorithms can be used to learn new parameterizations from the output of a three-dimensional high-resolution atmospheric model, while obeying physical constraints such as energy conservation. Implementing these parameterizations in the atmospheric model at coarse resolution leads to stable simulations that replicate the climate of the high-resolution simulation, and capture important statistics such as precipitation extremes. I will also discuss how machine-learning parameterizations can give further physical insights into the parameterization problem. Specifically, I will show how machine-learning algorithms combined with explainable artificial intelligence tools can be used to better understand the relationship between large-scale fields and subgrid processes.
Event Organizers: Dr. Roy Barkan and Dr. Asaf Inbal