A derecho climatology (2004–2021) in the United States based on machine learning identification of bow echoes

作者：Jianfeng Li, Andrew Geiss, Zhe Feng, L. Ruby Leung, Yun Qian, Wenjun Cui · 发表于：Earth system science data · 年份：2025 · DOI：10.5194/essd-17-3721-2025 · 被引用次数：4 · 研究领域：Wind and Air Flow Studies、Fire effects on ecosystems、Meteorological Phenomena and Simulations

Abstract. Due to their persistent widespread severe winds, derechos pose significant threats to human safety and property, with impacts comparable to many tornadoes and hurricanes. Yet, automated detection of derechos remains challenging due to the absence of spatiotemporally continuous observations and the complex criteria employed to define the phenomenon. This study presents an objective derecho detection approach capable of automatically identifying derechos through both observations and model results. The approach is grounded in a physically based definition of derechos and integrates three algorithms: (1) the Python Flexible Object Tracker (PyFLEXTRKR) algorithm to track mesoscale convective systems (MCSs), (2) a semantic segmentation convolutional neural network to identify bow echoes, and (3) a comprehensive classification algorithm to detect derechos within MCS life cycles and distinguish derecho-producing from non-derecho-producing MCSs. Using this approach, we developed a novel high-resolution (4 km and hourly) observational dataset of derechos and accompanying derecho-producing MCSs over the United States east of the Rocky Mountains from 2004 to 2021. The dataset consists of two subsets based on different gust speed data sources and is analyzed to document the climatology of derechos in the United States. On average, 12–15 derechos are identified per year, aligning with previous estimations (∼6–21 events annually). The spatial distribution and seasonal variation p...