Assessing the Utility of Volumetric Motion Fields for Radar-based Precipitation Nowcasting with Physics-informed Deep Learning

TL;DR

This paper introduces a physics-informed deep learning framework for estimating altitude-wise motion fields from volumetric radar data to improve precipitation nowcasting, analyzing vertical coherence and its impact on forecasting accuracy.

Contribution

The work presents a novel deep learning approach that estimates three-dimensional motion fields from volumetric radar data, emphasizing vertical coherence analysis.

Findings

Estimated motion fields show strong vertical coherence across altitude levels.

Limited improvement over 2D methods in regions with vertically coherent precipitation.

Framework offers a tool for analyzing motion structure in volumetric geospatial data.

Abstract

Estimating motion from spatiotemporal geoscientific data is a fundamental component of many environmental modeling and forecasting tasks. In this work, we propose a physics-informed deep learning framework for estimating altitude-wise motion fields directly from volumetric radar reflectivity data. The model utilizes a fully differentiable semi-Lagrangian extrapolation operator to process three-dimensional inputs as independent horizontal slice sequences, enabling efficient inference of horizontal motion across multiple altitude levels. Using a multi-year radar dataset from Central Europe, we evaluate the impact of altitude-wise motion estimation on extrapolation-based precipitation forecasting and conduct a systematic dataset-scale analysis of inter-altitude motion consistency. The results show that the estimated motion fields exhibit strong vertical coherence, with high correlation across altitude levels, which results in limited improvement over traditional two-dimensional approach in this setting. The proposed framework provides a general tool for efficiently analyzing motion structure in volumetric geospatial data. The findings indicate that, in regions dominated by vertically coherent precipitation systems, the added complexity of volumetric motion modeling may offer limited benefit, warranting careful consideration in the design of efficient spatiotemporal advection models.