ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs

TL;DR

ClimODE introduces a physics-informed neural ODE framework for weather forecasting that models advection-based dynamics, conserving physical quantities and providing uncertainty estimates, outperforming existing data-driven methods.

Contribution

This work presents ClimODE, a novel neural ODE model incorporating physics principles for improved weather prediction with fewer parameters.

Findings

Outperforms existing data-driven forecasting methods.

Uses significantly fewer parameters than previous models.

Provides uncertainty quantification in predictions.

Abstract

Climate and weather 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.