Scholarlink

<p>This study evaluates Pangu-Weather, a machine-learning-based weather prediction (MLWP) model, for its ability to reduce errors in numerical predictions of significant wave height (SWH). SWH predictions from the SWAN wave model were driven by 10&#xa0;m wind fields from Pangu-Weather, and error assessments were conducted at 50 observation stations along the Japanese coast over 52 seven-day periods in 2022. For comparison, meteorological forcing from the Weather Research and Forecasting (WRF) numerical weather prediction (NWP) model was also applied. When used as meteorological forcing, Pangu-Weather performed comparably to WRF in most cases, but showed a clear advantage for observed SWH &lt; 1.0&#xa0;m. In contrast, WRF showed better performance for observed SWH ≥ 1.0&#xa0;m. This is partly because Pangu-Weather often struggles to predict severe meteorological events (e.g., typhoons and bomb cyclones) and their associated SWH. These findings, within the scope of this study, indicate that MLWP forcing has the potential to serve as an alternative to NWP for SWH prediction, while further work is needed to extend this skill to rarer high-impact events.</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

Assessing machine-learning-based weather forcing in significant wave height prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月6日

查看全文
  • Fuuki Ogawa,
  • Tomoki Shirai,
  • Tatsumi Harada,
  • Masashi Tanaka,
  • Yurie Itagaki,
  • Taro Arikawa,
  • Tomoya Shibayama

摘要

This study evaluates Pangu-Weather, a machine-learning-based weather prediction (MLWP) model, for its ability to reduce errors in numerical predictions of significant wave height (SWH). SWH predictions from the SWAN wave model were driven by 10 m wind fields from Pangu-Weather, and error assessments were conducted at 50 observation stations along the Japanese coast over 52 seven-day periods in 2022. For comparison, meteorological forcing from the Weather Research and Forecasting (WRF) numerical weather prediction (NWP) model was also applied. When used as meteorological forcing, Pangu-Weather performed comparably to WRF in most cases, but showed a clear advantage for observed SWH < 1.0 m. In contrast, WRF showed better performance for observed SWH ≥ 1.0 m. This is partly because Pangu-Weather often struggles to predict severe meteorological events (e.g., typhoons and bomb cyclones) and their associated SWH. These findings, within the scope of this study, indicate that MLWP forcing has the potential to serve as an alternative to NWP for SWH prediction, while further work is needed to extend this skill to rarer high-impact events.