Transformer-based nowcasting of radar composites from satellite images for severe weather

TL;DR

This paper introduces a Transformer-based model that uses satellite imagery to nowcast radar data for severe weather prediction up to two hours ahead, bridging the gap between satellite and ground-based observations.

Contribution

The study presents a novel deep learning approach that leverages satellite data for radar nowcasting, enabling large-scale, high-accuracy weather prediction without relying solely on ground-based radar.

Findings

Model accurately predicts radar fields under severe weather conditions.

Infrared channel at 10.3 μm contains significant predictive information.

Lightning data are highly important for severe weather nowcasting.

Abstract

Weather radar data are critical for nowcasting and an integral component of numerical weather prediction models. While weather radar data provide valuable information at high resolution, their ground-based nature limits their availability, which impedes large-scale applications. In contrast, meteorological satellites cover larger domains but with coarser resolution. However, with the rapid advancements in data-driven methodologies and modern sensors aboard geostationary satellites, new opportunities are emerging to bridge the gap between ground- and space-based observations, ultimately leading to more skillful weather prediction with high accuracy. Here, we present a Transformer-based model for nowcasting ground-based radar image sequences using satellite data up to two hours lead time. Trained on a dataset reflecting severe weather conditions, the model predicts radar fields occurring under different weather phenomena and shows robustness against rapidly growing/decaying fields and complex field structures. Model interpretation reveals that the infrared channel centered at 10.3 $\mu m$ (C13) contains skillful information for all weather conditions, while lightning data have the highest relative feature importance in severe weather conditions, particularly in shorter lead times. The model can support precipitation nowcasting across large domains without an explicit need for radar towers, enhance numerical weather prediction and hydrological models, and provide radar proxy for data-scarce regions. Moreover, the open-source framework facilitates progress towards operational data-driven nowcasting.