Fusion of rain radar images and wind forecasts in a deep learning model applied to rain nowcasting

TL;DR

This paper demonstrates that combining rainfall radar images with wind forecasts in a deep learning model significantly improves short-term rain nowcasting accuracy, especially for high precipitation events.

Contribution

The study introduces a novel deep learning approach that fuses radar and wind data, outperforming models using only radar data and traditional optical flow methods.

Findings

8% improvement over optical flow F1-score for moderate rain

7% improvement over radar-only models

Enhanced stability and accuracy for high rainfall predictions

Abstract

Short- or mid-term rainfall forecasting is a major task with several environmental applications such as agricultural management or flood risk monitoring. Existing data-driven approaches, especially deep learning models, have shown significant skill at this task, using only rainfall radar images as inputs. In order to determine whether using other meteorological parameters such as wind would improve forecasts, we trained a deep learning model on a fusion of rainfall radar images and wind velocity produced by a weather forecast model. The network was compared to a similar architecture trained only on radar data, to a basic persistence model and to an approach based on optical flow. Our network outperforms by 8% the F1-score calculated for the optical flow on moderate and higher rain events for forecasts at a horizon time of 30 min. Furthermore, it outperforms by 7% the same architecture trained using only rainfall radar images. Merging rain and wind data has also proven to stabilize the training process and enabled significant improvement especially on the difficult-to-predict high precipitation rainfalls.