利用新型时空神经网络模型,通过风速数据融合改进天气雷达回波推断法

IF 1.5 4区 地球科学 Q4 METEOROLOGY & ATMOSPHERIC SCIENCES 热带气象学报 Pub Date : 2023-12-01 DOI:10.3724/j.1006-8775.2023.036
Huan-tong Geng, Bo-yang Xie, Xiao-yan Ge, Jin-zhong Min, Xiao-ran Zhuang
{"title":"利用新型时空神经网络模型,通过风速数据融合改进天气雷达回波推断法","authors":"Huan-tong Geng, Bo-yang Xie, Xiao-yan Ge, Jin-zhong Min, Xiao-ran Zhuang","doi":"10.3724/j.1006-8775.2023.036","DOIUrl":null,"url":null,"abstract":": Weather radar echo extrapolation plays a crucial role in weather forecasting. However, traditional weather radar echo extrapolation methods are not very accurate and do not make full use of historical data. Deep learning algorithms based on Recurrent Neural Networks also have the problem of accumulating errors. Moreover, it is difficult to obtain higher accuracy by relying on a single historical radar echo observation. Therefore, in this study, we constructed the Fusion GRU module, which leverages a cascade structure to effectively combine radar echo data and mean wind data. We also designed the Top Connection so that the model can capture the global spatial relationship to construct constraints on the predictions. Based on the Jiangsu Province dataset, we compared some models. The results show that our proposed model, Cascade Fusion Spatiotemporal Network (CFSN), improved the critical success index (CSI) by 10.7% over the baseline at the threshold of 30 dBZ. Ablation experiments further validated the effectiveness of our model. Similarly, the CSI of the complete CFSN was 0.004 higher than the suboptimal solution without the cross-attention module at the threshold of 30 dBZ.","PeriodicalId":17432,"journal":{"name":"热带气象学报","volume":"55 ","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Improved Weather Radar Echo Extrapolation Through Wind Speed Data Fusion Using a New Spatiotemporal Neural Network Model\",\"authors\":\"Huan-tong Geng, Bo-yang Xie, Xiao-yan Ge, Jin-zhong Min, Xiao-ran Zhuang\",\"doi\":\"10.3724/j.1006-8775.2023.036\",\"DOIUrl\":null,\"url\":null,\"abstract\":\": Weather radar echo extrapolation plays a crucial role in weather forecasting. However, traditional weather radar echo extrapolation methods are not very accurate and do not make full use of historical data. Deep learning algorithms based on Recurrent Neural Networks also have the problem of accumulating errors. Moreover, it is difficult to obtain higher accuracy by relying on a single historical radar echo observation. Therefore, in this study, we constructed the Fusion GRU module, which leverages a cascade structure to effectively combine radar echo data and mean wind data. We also designed the Top Connection so that the model can capture the global spatial relationship to construct constraints on the predictions. Based on the Jiangsu Province dataset, we compared some models. The results show that our proposed model, Cascade Fusion Spatiotemporal Network (CFSN), improved the critical success index (CSI) by 10.7% over the baseline at the threshold of 30 dBZ. Ablation experiments further validated the effectiveness of our model. Similarly, the CSI of the complete CFSN was 0.004 higher than the suboptimal solution without the cross-attention module at the threshold of 30 dBZ.\",\"PeriodicalId\":17432,\"journal\":{\"name\":\"热带气象学报\",\"volume\":\"55 \",\"pages\":\"\"},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2023-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"热带气象学报\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.3724/j.1006-8775.2023.036\",\"RegionNum\":4,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"METEOROLOGY & ATMOSPHERIC SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"热带气象学报","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.3724/j.1006-8775.2023.036","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

:天气雷达回波外推法在天气预报中起着至关重要的作用。然而,传统的天气雷达回波外推方法并不十分准确,也没有充分利用历史数据。基于递归神经网络的深度学习算法也存在误差累积的问题。此外,依靠单一的雷达回波历史观测数据很难获得更高的精度。因此,在本研究中,我们构建了融合 GRU 模块,利用级联结构将雷达回波数据和平均风数据有效地结合起来。我们还设计了顶部连接,使模型能够捕捉全局空间关系,为预测构建约束条件。基于江苏省的数据集,我们对一些模型进行了比较。结果表明,在阈值为 30 dBZ 时,我们提出的级联融合时空网络(CFSN)模型比基线模型的临界成功指数(CSI)提高了 10.7%。消融实验进一步验证了我们模型的有效性。同样,在阈值为 30 dBZ 时,完整 CFSN 的 CSI 比没有交叉注意模块的次优方案高 0.004。
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
Improved Weather Radar Echo Extrapolation Through Wind Speed Data Fusion Using a New Spatiotemporal Neural Network Model
: Weather radar echo extrapolation plays a crucial role in weather forecasting. However, traditional weather radar echo extrapolation methods are not very accurate and do not make full use of historical data. Deep learning algorithms based on Recurrent Neural Networks also have the problem of accumulating errors. Moreover, it is difficult to obtain higher accuracy by relying on a single historical radar echo observation. Therefore, in this study, we constructed the Fusion GRU module, which leverages a cascade structure to effectively combine radar echo data and mean wind data. We also designed the Top Connection so that the model can capture the global spatial relationship to construct constraints on the predictions. Based on the Jiangsu Province dataset, we compared some models. The results show that our proposed model, Cascade Fusion Spatiotemporal Network (CFSN), improved the critical success index (CSI) by 10.7% over the baseline at the threshold of 30 dBZ. Ablation experiments further validated the effectiveness of our model. Similarly, the CSI of the complete CFSN was 0.004 higher than the suboptimal solution without the cross-attention module at the threshold of 30 dBZ.
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
热带气象学报
热带气象学报 METEOROLOGY & ATMOSPHERIC SCIENCES-
CiteScore
1.80
自引率
8.30%
发文量
2793
审稿时长
6-12 weeks
期刊介绍: Information not localized
期刊最新文献
Correcting Black Carbon Absorption Measurements with Micro-aethalometer Model 200: Insights from Comparative Analysis Improved Weather Radar Echo Extrapolation Through Wind Speed Data Fusion Using a New Spatiotemporal Neural Network Model Interannual Variation and Statistical Prediction of Summer Dry and Hot Days in South China from 1970 to 2018 Observational and Mechanistic Analysis of a Nighttime Warm-Sector Heavy Rainfall Event Within the Subtropical High over the Southeastern Coast of China Adaptive Wind Gust and Associated Gust-factor Model for the Gust-producing Weather over the Northern South China Sea
×
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