Do Echo Top Heights Improve Deep Learning Nowcasts?

TL;DR

This study investigates whether incorporating Echo Top Height (ETH) as an auxiliary input improves deep learning-based precipitation nowcasting, revealing mixed results and highlighting the complexity of using vertical radar information.

Contribution

The paper introduces a deep learning model that uses ETH alongside radar reflectivity for nowcasting, providing insights into the benefits and limitations of vertical radar data.

Findings

ETH improves skill at low rain-rate thresholds

Models with ETH underestimate high-intensity rainfall

Inconsistent results across different case studies

Abstract

Precipitation nowcasting -- the short-term prediction of rainfall using recent radar observations -- is critical for weather-sensitive sectors such as transportation, agriculture, and disaster mitigation. While recent deep learning models have shown promise in improving nowcasting skill, most approaches rely solely on 2D radar reflectivity fields, discarding valuable vertical information available in the full 3D radar volume. In this work, we explore the use of Echo Top Height (ETH), a 2D projection indicating the maximum altitude of radar reflectivity above a given threshold, as an auxiliary input variable for deep learning-based nowcasting. We examine the relationship between ETH and radar reflectivity, confirming its relevance for predicting rainfall intensity. We implement a single-pass 3D U-Net that processes both the radar reflectivity and ETH as separate input channels. While our models are able to leverage ETH to improve skill at low rain-rate thresholds, results are inconsistent at higher intensities and the models with ETH systematically underestimate precipitation intensity. Three case studies are used to illustrate how ETH can help in some cases, but also confuse the models and increase the error variance. Nonetheless, the study serves as a foundation for critically assessing the potential contribution of additional variables to nowcasting performance.