PACER: Physics Informed and Uncertainty Aware Climate Emulator
This work addresses the problem of slow climate simulations for researchers and policymakers by offering a more efficient emulator, though it is incremental in advancing physics-informed ML methods.
The paper tackles the computational inefficiency of physics-based climate models by proposing PACER, a lightweight deep learning emulator that integrates physical laws and quantifies uncertainty, achieving stable 10-year temperature field emulation across 20 climate models with 2.1M parameters.
Physics based numerical climate models serve as critical tools for evaluating the effects of climate change and projecting future climate scenarios. However, the reliance on numerical simulations of physical equations renders them computationally intensive and inefficient. While deep learning methodologies have made significant progress in weather forecasting, they are still unstable for longer roll-out climate emulation task. Here, we propose PACER, a relatively lightweight 2.1M parameter Physics Informed Uncertainty Aware Climate EmulatoR. PACER is trained across is trained across varying spatial resolutions and physics based climate models, enabling faithful and stable emulation of temperature fields at multiple surface levels over a 10 year horizon. We propose an auto-regressive ODE-SDE framework for climate emulation that integrates the fundamental physical law of advection, while being trained under a negative log-likelihood objective to enable principled uncertainty quantification of stochastic variability. We show PACER's emulation performance across 20 climate models outperforming relevant baselines and advancing towards explicit physics infusion in ML emulator.