Scholarlink

<p>The accurate cumulative precipitation forecasts are essential for monitoring water resources and natural disasters. The combination of deep learning and big data has become a new direction for precipitation forecasting. However, the current large models are still lacking in-situ data verification. To accomplish this goal, the precipitation forecasting performance of a state-of-the-art model GraphCast was evaluated. Using the cumulative precipitation data from 2393 observation stations for the 1–3 day period as a reference, we assessed the cumulative precipitation in mainland China region for the 1–3 day period from 2020 to 2021, utilizing a high-resolution model with 0.25° × 0.25° grid spacing and 13 layers of parameters. The precipitation of European Centre for Medium-Range Weather Forecasts (ECMWF) was also compared. The results show that: (1) During the 2020-2021 period, for the 1-day, 2-day, and 3-day cumulative precipitation forecasts, the Root Mean Square Error (RMSE) values of GraphCast were primarily between 0.46 to 9.38 mm/d, 0.44 to 9.06 mm/d, and 0.44 to 9.06 mm/d, respectively. The Mean Error (ME) values were mainly between −&#xa0;0.595 to 1.705 (0.01 mm). (2) As the forecast period extends, the forecasting capability of GraphCast declines. (3) In the 1–3 day cumulative precipitation forecasts for various stations in mainland China, GraphCast demonstrates higher predictive accuracy than ECMWF. (4) Compared to ECMWF, GraphCast demonstrated the best forecast performance in the temperate humid and semi-humid regions of Northeast China, with the RMSE being approximately 12<InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_98944_Article_IEq3.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation> higher. Our study indicates that GraphCast demonstrates significant potential and higher accuracy in precipitation forecasting.</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

Evaluation of precipitation forecasting base on GraphCast over mainland China

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月28日

查看全文
  • Zihuang Yan,
  • Xianghui Lu,
  • Lifeng Wu,
  • Fa Liu,
  • Rangjian Qiu,
  • Yaokui Cui,
  • Xin Ma

摘要

The accurate cumulative precipitation forecasts are essential for monitoring water resources and natural disasters. The combination of deep learning and big data has become a new direction for precipitation forecasting. However, the current large models are still lacking in-situ data verification. To accomplish this goal, the precipitation forecasting performance of a state-of-the-art model GraphCast was evaluated. Using the cumulative precipitation data from 2393 observation stations for the 1–3 day period as a reference, we assessed the cumulative precipitation in mainland China region for the 1–3 day period from 2020 to 2021, utilizing a high-resolution model with 0.25° × 0.25° grid spacing and 13 layers of parameters. The precipitation of European Centre for Medium-Range Weather Forecasts (ECMWF) was also compared. The results show that: (1) During the 2020-2021 period, for the 1-day, 2-day, and 3-day cumulative precipitation forecasts, the Root Mean Square Error (RMSE) values of GraphCast were primarily between 0.46 to 9.38 mm/d, 0.44 to 9.06 mm/d, and 0.44 to 9.06 mm/d, respectively. The Mean Error (ME) values were mainly between − 0.595 to 1.705 (0.01 mm). (2) As the forecast period extends, the forecasting capability of GraphCast declines. (3) In the 1–3 day cumulative precipitation forecasts for various stations in mainland China, GraphCast demonstrates higher predictive accuracy than ECMWF. (4) Compared to ECMWF, GraphCast demonstrated the best forecast performance in the temperate humid and semi-humid regions of Northeast China, with the RMSE being approximately 12 \(\%\) higher. Our study indicates that GraphCast demonstrates significant potential and higher accuracy in precipitation forecasting.