Deep learning methods dominate short-term high-resolution precipitation nowcasting in terms of prediction error. However, their operational usability is limited by difficulties explaining dynamics behind the predictions, which are smoothed out and missing the high-frequency features due to optimizing for mean error loss functions. We experiment with hand-engineering of the advection-diffusion differential equation into a PhyCell to introduce more accurate physical prior to a PhyDNet model that disentangles physical and residual dynamics. Results indicate that while PhyCell can learn the intended dynamics, training of PhyDNet remains driven by loss optimization, resulting in a model with the same prediction capabilities.
@article{arxiv.2301.11707,
title = {Improving deep learning precipitation nowcasting by using prior knowledge},
author = {Matej Choma and Petr Šimánek and Jakub Bartel},
journal= {arXiv preprint arXiv:2301.11707},
year = {2023}
}