HyPhAICC v1.0: a hybrid physics–AI approach for probability fields advection shown through an application to cloud cover nowcasting

Rachid El Montassir, Olivier Pannekoucke, Corentin Lapeyre

Geoscientific model development · 10 September 2024 · Météo-France (incl. CNRM)

In one sentence. Hybrid model enforces advection physics as a hard constraint on a U-Net for cloud cover nowcasting, beating EUMETSAT EXIM and a plain U-Net with one-third of the data.

Abstract

Abstract. This work proposes a hybrid approach that combines Physics and Artificial Intelligence (AI) for cloud cover nowcasting. It addresses the limitations of traditional deep learning methods in producing realistic and physically consistent results that can generalize to unseen data. The proposed approach enforces a physical behaviour. In the first model, denoted HyPhAI-1, a multi-level advection dynamics is considered as a hard constraint for a trained U-Net model. Our experiments show that the hybrid formulation outperforms not only traditional deep learning methods, but also the EUMETSAT Extrapolated Imagery model (EXIM) in terms of both qualitative and quantitative results. In particular, we illustrate that the hybrid model preserves more details and achieves higher scores based on similarity metrics in comparison to the U-Net. Remarkably, these improvements are achieved while using only one-third of the data required by the other models. Another model, denoted HyPhAI-2, adds a source term to the advection equation, it impaired the visual rendering but displayed the best performance in terms of Accuracy. These results suggest that the proposed hybrid Physics-AI architecture provides a promising solution to overcome the limitations of classical AI methods, and contributes to open up new possibilities for combining physical knowledge with deep learning models.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.