PIMRL: Physics-Informed Multi-Scale Recurrent Learning for Spatiotemporal Prediction
By: Han Wan , Qi Wang , Yuan Mi and more
Potential Business Impact:
Predicts weather and science events more accurately.
Simulation of spatiotemporal systems governed by partial differential equations is widely applied in fields such as biology, chemistry, aerospace dynamics, and meteorology. Traditional numerical methods incur high computational costs due to the requirement of small time steps for accurate predictions. While machine learning has reduced these costs, long-term predictions remain challenged by error accumulation, particularly in scenarios with insufficient data or varying time scales, where stability and accuracy are compromised. Existing methods often neglect the effective utilization of multi-scale data, leading to suboptimal robustness in predictions. To address these issues, we propose a novel multi-scale learning framework, namely, the Physics-Informed Multi-Scale Recurrent Learning (PIMRL), to effectively leverage multi-scale data for spatiotemporal dynamics prediction. The PIMRL framework comprises two modules: the micro-scale module embeds physical knowledge into neural networks via pretraining, and the macro-scale module adopts a data-driven approach to learn the temporal evolution of physics in the latent space. Experimental results demonstrate that the PIMRL framework consistently achieves state-of-the-art performance across five benchmark datasets ranging from one to three dimensions, showing average improvements of over 9\% in both RMSE and MAE evaluation metrics, with maximum enhancements reaching up to 80%.
Similar Papers
Physics-informed Modularized Neural Network for Advanced Building Control by Deep Reinforcement Learning
Systems and Control
Saves energy by teaching computers to control buildings.
Physics-Informed Inference Time Scaling via Simulation-Calibrated Scientific Machine Learning
Numerical Analysis
Fixes computer math problems using physics rules.
Plug-and-Play Physics-informed Learning using Uncertainty Quantified Port-Hamiltonian Models
Robotics
Helps robots predict danger, even when surprised.