Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting
This work addresses the need for efficient and physically consistent weather forecasting methods, offering a novel hybrid approach that could benefit meteorology and climate science, though it builds incrementally on existing physics-informed deep learning techniques.
The paper tackles the problem of computationally intensive and physically incomplete weather forecasting by proposing PhyDL-NWP, a physics-guided deep learning framework that integrates physical equations with data-driven models, achieving up to 170x faster inference with only 55K parameters while improving forecasting performance and physical consistency.
Weather forecasting is essential but remains computationally intensive and physically incomplete in traditional numerical weather prediction (NWP) methods. Deep learning (DL) models offer efficiency and accuracy but often ignore physical laws, limiting interpretability and generalization. We propose PhyDL-NWP, a physics-guided deep learning framework that integrates physical equations with latent force parameterization into data-driven models. It predicts weather variables from arbitrary spatiotemporal coordinates, computes physical terms via automatic differentiation, and uses a physics-informed loss to align predictions with governing dynamics. PhyDL-NWP enables resolution-free downscaling by modeling weather as a continuous function and fine-tunes pre-trained models with minimal overhead, achieving up to 170x faster inference with only 55K parameters. Experiments show that PhyDL-NWP improves both forecasting performance and physical consistency.