Espresso:一个从卫星观测估计降水的全球深度学习模型

Léa Berthomier, Laurent Perier
{"title":"Espresso:一个从卫星观测估计降水的全球深度学习模型","authors":"Léa Berthomier, Laurent Perier","doi":"10.3390/meteorology2040025","DOIUrl":null,"url":null,"abstract":"Estimating precipitation is of critical importance to climate systems and decision-making processes. This paper presents Espresso, a deep learning model designed for estimating precipitation from satellite observations on a global scale. Conventional methods, like ground-based radars, are limited in terms of spatial coverage. Satellite observations, on the other hand, allow global coverage. Combined with deep learning methods, these observations offer the opportunity to address the challenge of estimating precipitation on a global scale. This research paper presents the development of a deep learning model using geostationary satellite data as input and generating instantaneous rainfall rates, calibrated using data from the Global Precipitation Measurement Core Observatory (GPMCO). The performance impact of various input data configurations on Espresso was investigated. These configurations include a sequence of four images from geostationary satellites and the optimal selection of channels. Additional descriptive features were explored to enhance the model’s robustness for global applications. When evaluated against the GPMCO test set, Espresso demonstrated highly accurate precipitation estimation, especially within equatorial regions. A comparison against six other operational products using multiple metrics indicated its competitive performance. The model’s superior storm localization and intensity estimation were further confirmed through visual comparisons in case studies. Espresso has been incorporated as an operational product at Météo-France, delivering high-quality, real-time global precipitation estimates every 30 min.","PeriodicalId":100061,"journal":{"name":"Agricultural Meteorology","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Espresso: A Global Deep Learning Model to Estimate Precipitation from Satellite Observations\",\"authors\":\"Léa Berthomier, Laurent Perier\",\"doi\":\"10.3390/meteorology2040025\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Estimating precipitation is of critical importance to climate systems and decision-making processes. This paper presents Espresso, a deep learning model designed for estimating precipitation from satellite observations on a global scale. Conventional methods, like ground-based radars, are limited in terms of spatial coverage. Satellite observations, on the other hand, allow global coverage. Combined with deep learning methods, these observations offer the opportunity to address the challenge of estimating precipitation on a global scale. This research paper presents the development of a deep learning model using geostationary satellite data as input and generating instantaneous rainfall rates, calibrated using data from the Global Precipitation Measurement Core Observatory (GPMCO). The performance impact of various input data configurations on Espresso was investigated. These configurations include a sequence of four images from geostationary satellites and the optimal selection of channels. Additional descriptive features were explored to enhance the model’s robustness for global applications. When evaluated against the GPMCO test set, Espresso demonstrated highly accurate precipitation estimation, especially within equatorial regions. A comparison against six other operational products using multiple metrics indicated its competitive performance. The model’s superior storm localization and intensity estimation were further confirmed through visual comparisons in case studies. Espresso has been incorporated as an operational product at Météo-France, delivering high-quality, real-time global precipitation estimates every 30 min.\",\"PeriodicalId\":100061,\"journal\":{\"name\":\"Agricultural Meteorology\",\"volume\":\"41 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-09-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Agricultural Meteorology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/meteorology2040025\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Agricultural Meteorology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/meteorology2040025","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

估算降水对气候系统和决策过程至关重要。本文介绍了Espresso,这是一个深度学习模型,旨在从全球范围的卫星观测中估计降水。传统的方法,如地面雷达,在空间覆盖方面是有限的。另一方面,卫星观测可以覆盖全球。与深度学习方法相结合,这些观测结果为解决在全球范围内估计降水的挑战提供了机会。本文介绍了一种深度学习模型的开发,该模型使用地球静止卫星数据作为输入,并使用全球降水测量核心观测站(GPMCO)的数据进行校准,生成瞬时降雨率。研究了不同输入数据配置对Espresso性能的影响。这些配置包括来自地球静止卫星的四幅图像序列和信道的最佳选择。研究了其他描述性特征,以增强模型对全局应用的鲁棒性。当对GPMCO测试集进行评估时,Espresso显示出高度准确的降水估计,特别是在赤道地区。使用多个指标与其他六种运营产品进行比较,表明其具有竞争力。通过实例的目视比较,进一步证实了该模式在风暴定位和强度估计方面的优越性。Espresso已被纳入msamtsamo - france的运营产品,每30分钟提供高质量的实时全球降水估计。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Espresso: A Global Deep Learning Model to Estimate Precipitation from Satellite Observations
Estimating precipitation is of critical importance to climate systems and decision-making processes. This paper presents Espresso, a deep learning model designed for estimating precipitation from satellite observations on a global scale. Conventional methods, like ground-based radars, are limited in terms of spatial coverage. Satellite observations, on the other hand, allow global coverage. Combined with deep learning methods, these observations offer the opportunity to address the challenge of estimating precipitation on a global scale. This research paper presents the development of a deep learning model using geostationary satellite data as input and generating instantaneous rainfall rates, calibrated using data from the Global Precipitation Measurement Core Observatory (GPMCO). The performance impact of various input data configurations on Espresso was investigated. These configurations include a sequence of four images from geostationary satellites and the optimal selection of channels. Additional descriptive features were explored to enhance the model’s robustness for global applications. When evaluated against the GPMCO test set, Espresso demonstrated highly accurate precipitation estimation, especially within equatorial regions. A comparison against six other operational products using multiple metrics indicated its competitive performance. The model’s superior storm localization and intensity estimation were further confirmed through visual comparisons in case studies. Espresso has been incorporated as an operational product at Météo-France, delivering high-quality, real-time global precipitation estimates every 30 min.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Specific Features of the Land-Sea Contrast of Cloud Liquid Water Path in Northern Europe as Obtained from the Observations by the SEVIRI Instrument: Artefacts or Reality? Air Temperature Intermittency and Photofragment Excitation Espresso: A Global Deep Learning Model to Estimate Precipitation from Satellite Observations No City Left Behind: Building Climate Policy Bridges between the North and South Characteristics of Convective Parameters Derived from Rawinsonde and ERA5 Data Associated with Hailstorms in Northeastern Romania
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1