Scholarlink

<p>Freezing rain (FR) event is a highly catastrophic event, significantly impact human habitats. However, there is still a substantial lack of gridded FR data. Here, we present a comprehensive gridded FR dataset across China from January 1, 2000, to December 31, 2019, utilizing station data from the China Meteorological Administration combined with ERA5-land and pressure level data. Employing Deep Kernel Learning (DKL), we effectively classified and predicted FR occurrences, demonstrating significant advancements in capturing complex atmospheric conditions conducive to FR. The DKL model, validated against ERA5 data for the winter of 2024 and the Ramer Scheme in 2008, 2011, and 2018, showcases superior classified power over traditional methods, achieving remarkable accuracy of 0.991, Area Under the Curve (AUC) of 0.999, recall of 0.973, and precision of 0.989. The implications of this research are profound, offering a robust database for academic and practical applications in weather forecasting, climate modelling, and disaster management, thereby enhancing our understanding and mitigation strategies for FR impacts.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A 6-hourly 0.1° resolution freezing rain dataset of China during 2000–2019 based on deep kernel learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年2月11日

查看全文
  • Junfei Liu,
  • Kai Liu,
  • Ming Wang

摘要

Freezing rain (FR) event is a highly catastrophic event, significantly impact human habitats. However, there is still a substantial lack of gridded FR data. Here, we present a comprehensive gridded FR dataset across China from January 1, 2000, to December 31, 2019, utilizing station data from the China Meteorological Administration combined with ERA5-land and pressure level data. Employing Deep Kernel Learning (DKL), we effectively classified and predicted FR occurrences, demonstrating significant advancements in capturing complex atmospheric conditions conducive to FR. The DKL model, validated against ERA5 data for the winter of 2024 and the Ramer Scheme in 2008, 2011, and 2018, showcases superior classified power over traditional methods, achieving remarkable accuracy of 0.991, Area Under the Curve (AUC) of 0.999, recall of 0.973, and precision of 0.989. The implications of this research are profound, offering a robust database for academic and practical applications in weather forecasting, climate modelling, and disaster management, thereby enhancing our understanding and mitigation strategies for FR impacts.