Climate Forecasting with Physics-Informed Neural ODEs

Topic: ClimODE: Climate Forecasting With Physics-informed Neural ODEs

Abstract:

Climate prediction traditionally relies on complex numerical simulations of atmospheric physics. Deep learning approaches, such as transformers, have recently challenged the simulation paradigm with complex network forecasts. However, they often act as data-driven black-box models that neglect the underlying physics and lack uncertainty quantification. We address these limitations with ClimODE, a spatiotemporal continuous-time process that implements a key principle of advection from statistical mechanics, namely, weather changes due to a spatial movement of quantities over time. ClimODE models precise weather evolution with value-conserving dynamics, learning global weather transport as a neural flow, which also enables estimating the uncertainty in predictions. Our approach outperforms existing data-driven methods in global and regional forecasting with an order of magnitude smaller parameterization, establishing a new state of the art.

Speaker(s):

Yogesh Verma is a PhD candidate at Aalto University, Finland. Prior to this, he obtained his Master’s from IISER Mohali and worked at CERN and University of Zurich. He is interested in physics inspired deep learning to model dynamical complex systems such as time-series and its application in AI4Science, molecules, and drug design.