Fully Differentiable Lagrangian Convolutional Neural Network for Physics-Informed Precipitation Nowcasting

TL;DR

This paper introduces LUPIN, a fully differentiable Lagrangian CNN for precipitation nowcasting that combines physics-informed modeling with deep learning, enabling end-to-end training and outperforming existing benchmarks.

Contribution

We propose LUPIN, a novel Lagrangian CNN architecture that integrates physics-based extrapolation with data-driven learning for improved precipitation forecasting.

Findings

LUPIN matches and exceeds benchmark performance.

The model enables end-to-end differentiable training.

It effectively captures mesoscale advection and precipitation dynamics.

Abstract

This paper presents a convolutional neural network model for precipitation nowcasting that combines data-driven learning with physics-informed domain knowledge. We propose LUPIN, a Lagrangian Double U-Net for Physics-Informed Nowcasting, that draws from existing extrapolation-based nowcasting methods. It consists of a U-Net that dynamically produces mesoscale advection motion fields, a differentiable semi-Lagrangian extrapolation operator, and an advection-free U-Net capturing the growth and decay of precipitation over time. Using our approach, we successfully implement the Lagrangian convolutional neural network for precipitation nowcasting in a fully differentiable and GPU-accelerated manner. This allows for end-to-end training and inference, including the data-driven Lagrangian coordinate system transformation of the data at runtime. We evaluate the model and compare it with other related AI-based models both quantitatively and qualitatively in an extreme event case study. Based on our evaluation, LUPIN matches and even exceeds the performance of the chosen benchmarks, opening the door for other Lagrangian machine learning models.