PIANO: Physics-informed Dual Neural Operator for Precipitation Nowcasting
Seokhyun Chin, Junghwan Park, Woojin Cho
TL;DR
This work tackles global, accessible precipitation nowcasting by leveraging satellite imagery constrained by physics. It introduces PIANO, a physics-informed dual neural operator with V-NO learning velocity fields under a PINN loss and T-NO handling time stepping, followed by a Pix2Pix-based satellite-to-radar translation. Through a season-aware training regime on the Sat2RDR dataset, PIANO achieves competitive CSI for moderate rainfall and solid short-horizon performance for heavy rainfall, while showing low seasonal variability. The approach demonstrates robust, physically grounded nowcasting that can generalize beyond radar coverage and into data-sparse regions, establishing a promising baseline for physics-informed precipitation forecasting.
Abstract
Precipitation nowcasting, key for early warning of disasters, currently relies on computationally expensive and restrictive methods that limit access to many countries. To overcome this challenge, we propose precipitation nowcasting using satellite imagery with physics constraints for improved accuracy and physical consistency. We use a novel physics-informed dual neural operator (PIANO) structure to enforce the fundamental equation of advection-diffusion during training to predict satellite imagery using a PINN loss. Then, we use a generative model to convert satellite images to radar images, which are used for precipitation nowcasting. Compared to baseline models, our proposed model shows a notable improvement in moderate (4mm/h) precipitation event prediction alongside short-term heavy (8mm/h) precipitation event prediction. It also demonstrates low seasonal variability in predictions, indicating robustness for generalization. This study suggests the potential of the PIANO and serves as a good baseline for physics-informed precipitation nowcasting.