ConvLSTM 和 ConvGRU 在分类问题中的性能比较研究--以短时强降雨预警为例

IF 2.3 4区 地球科学 Q3 METEOROLOGY & ATMOSPHERIC SCIENCES Atmospheric and Oceanic Science Letters Pub Date : 2024-03-30 DOI:10.1016/j.aosl.2024.100494
Meng Zhou , Jingya Wu , Mingxuan Chen , Lei Han
{"title":"ConvLSTM 和 ConvGRU 在分类问题中的性能比较研究--以短时强降雨预警为例","authors":"Meng Zhou ,&nbsp;Jingya Wu ,&nbsp;Mingxuan Chen ,&nbsp;Lei Han","doi":"10.1016/j.aosl.2024.100494","DOIUrl":null,"url":null,"abstract":"<div><p>Convolutional long short-term memory (ConvLSTM) and convolutional gated recurrent unit (ConvGRU) are two widely adopted deep learning models that combine recurrent mechanisms with convolutional operations for spatiotemporal sequences forecasting. To clarify the convergence speed and classification ability of the above two models, using the same model architecture to predict the same classification problem is necessary. This research treats the district-level warning of short-duration heavy rainfall in Beijing as a binary classification problem in deep learning, and composite radar reflectivity data of the Beijing–Tianjin–Hebei radar network and rainfall data from automatic weather stations in Beijing are used for training and performance evaluation. The results show that the convergence speed of ConvGRU is approximately 25% faster than that of ConvLSTM. The early-warning performances of ConvLSTM and ConvGRU have similar trends with region, time, and rain intensity, but most of the scores of ConvLSTM are higher, and in a few cases, ConvGRU has higher scores.</p><p>摘要</p><p>卷积长短期记忆单元ConvLSTM和卷积门控循环单元ConvGRU是两种广泛应用的深度学习单元, 通过将循环机制与卷积运算相结合, 常常用于时空序列的预测. 为了明确上述两种模型的收敛速度和分类能力, 需要使用相同的模型架构对相同的分类问题进行预测. 本研究将北京短时强降水区级预警问题看作深度学习中的二分类问题, 使用京津冀雷达网的组合反射率数据和北京区域内的自动气象站降雨数据进行深度学习模型的训练和评估. 结果表明, ConvGRU的收敛速度比 ConvLSTM快约25%. ConvLSTM和ConvGRU的预警性能随地区, 时间, 降雨强度的变化趋势相似, 但大部分ConvLSTM的得分较高, 少数情况下ConvGRU的得分较高.</p></div>","PeriodicalId":47210,"journal":{"name":"Atmospheric and Oceanic Science Letters","volume":"17 4","pages":"Article 100494"},"PeriodicalIF":2.3000,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674283424000436/pdfft?md5=d082409c9531e54b588a9ddaef04a312&pid=1-s2.0-S1674283424000436-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Comparative study on the performance of ConvLSTM and ConvGRU in classification problems—taking early warning of short-duration heavy rainfall as an example\",\"authors\":\"Meng Zhou ,&nbsp;Jingya Wu ,&nbsp;Mingxuan Chen ,&nbsp;Lei Han\",\"doi\":\"10.1016/j.aosl.2024.100494\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Convolutional long short-term memory (ConvLSTM) and convolutional gated recurrent unit (ConvGRU) are two widely adopted deep learning models that combine recurrent mechanisms with convolutional operations for spatiotemporal sequences forecasting. To clarify the convergence speed and classification ability of the above two models, using the same model architecture to predict the same classification problem is necessary. This research treats the district-level warning of short-duration heavy rainfall in Beijing as a binary classification problem in deep learning, and composite radar reflectivity data of the Beijing–Tianjin–Hebei radar network and rainfall data from automatic weather stations in Beijing are used for training and performance evaluation. The results show that the convergence speed of ConvGRU is approximately 25% faster than that of ConvLSTM. The early-warning performances of ConvLSTM and ConvGRU have similar trends with region, time, and rain intensity, but most of the scores of ConvLSTM are higher, and in a few cases, ConvGRU has higher scores.</p><p>摘要</p><p>卷积长短期记忆单元ConvLSTM和卷积门控循环单元ConvGRU是两种广泛应用的深度学习单元, 通过将循环机制与卷积运算相结合, 常常用于时空序列的预测. 为了明确上述两种模型的收敛速度和分类能力, 需要使用相同的模型架构对相同的分类问题进行预测. 本研究将北京短时强降水区级预警问题看作深度学习中的二分类问题, 使用京津冀雷达网的组合反射率数据和北京区域内的自动气象站降雨数据进行深度学习模型的训练和评估. 结果表明, ConvGRU的收敛速度比 ConvLSTM快约25%. ConvLSTM和ConvGRU的预警性能随地区, 时间, 降雨强度的变化趋势相似, 但大部分ConvLSTM的得分较高, 少数情况下ConvGRU的得分较高.</p></div>\",\"PeriodicalId\":47210,\"journal\":{\"name\":\"Atmospheric and Oceanic Science Letters\",\"volume\":\"17 4\",\"pages\":\"Article 100494\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2024-03-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S1674283424000436/pdfft?md5=d082409c9531e54b588a9ddaef04a312&pid=1-s2.0-S1674283424000436-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Atmospheric and Oceanic Science Letters\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1674283424000436\",\"RegionNum\":4,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"METEOROLOGY & ATMOSPHERIC SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Atmospheric and Oceanic Science Letters","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1674283424000436","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

卷积长短时记忆(ConvLSTM)和卷积门控递归单元(ConvGRU)是两种被广泛采用的深度学习模型,它们将递归机制与卷积操作相结合,用于时空序列预测。为了明确上述两种模型的收敛速度和分类能力,有必要使用相同的模型架构来预测相同的分类问题。本研究将北京市短时强降雨区级预警作为深度学习中的二元分类问题,采用京津冀雷达网的雷达反射率复合数据和北京市自动气象站的降雨数据进行训练和性能评估。结果表明,ConvGRU 的收敛速度比 ConvLSTM 快约 25%。ConvLSTM 和 ConvGRU 的预警性能随区域、时间和雨强的变化趋势相似,但大多数情况下 ConvLSTM 的得分更高,少数情况下 ConvGRU 的得分更高。摘要卷积长短期记忆单元ConvLSTM和卷积门控循环单元ConvGRU是两种广泛应用的深度学习单元,通过将循环机制与卷积运算相结合,常常用于时空序列的预测。为了明确上述两种模型的收敛速度和分类能力,需要使用相同的模型架构对相同的分类问题进行预测。本研究将北京短时强降水区级预警问题看作深度学习中的二分类问题, 使用京津冀雷达网的组合反射率数据和北京区域内的自动气象站降雨数据进行深度学习模型的训练和评估。结果表明,ConvGRU 的收敛速度比 ConvLSTM 快约 25%。ConvLSTM和ConvGRU的预警性能随地区, 时间, 降雨强度的变化趋势相似, 但大部分ConvLSTM的得分较高, 少数情况下ConvGRU的得分较高.
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

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
Comparative study on the performance of ConvLSTM and ConvGRU in classification problems—taking early warning of short-duration heavy rainfall as an example

Convolutional long short-term memory (ConvLSTM) and convolutional gated recurrent unit (ConvGRU) are two widely adopted deep learning models that combine recurrent mechanisms with convolutional operations for spatiotemporal sequences forecasting. To clarify the convergence speed and classification ability of the above two models, using the same model architecture to predict the same classification problem is necessary. This research treats the district-level warning of short-duration heavy rainfall in Beijing as a binary classification problem in deep learning, and composite radar reflectivity data of the Beijing–Tianjin–Hebei radar network and rainfall data from automatic weather stations in Beijing are used for training and performance evaluation. The results show that the convergence speed of ConvGRU is approximately 25% faster than that of ConvLSTM. The early-warning performances of ConvLSTM and ConvGRU have similar trends with region, time, and rain intensity, but most of the scores of ConvLSTM are higher, and in a few cases, ConvGRU has higher scores.

摘要

卷积长短期记忆单元ConvLSTM和卷积门控循环单元ConvGRU是两种广泛应用的深度学习单元, 通过将循环机制与卷积运算相结合, 常常用于时空序列的预测. 为了明确上述两种模型的收敛速度和分类能力, 需要使用相同的模型架构对相同的分类问题进行预测. 本研究将北京短时强降水区级预警问题看作深度学习中的二分类问题, 使用京津冀雷达网的组合反射率数据和北京区域内的自动气象站降雨数据进行深度学习模型的训练和评估. 结果表明, ConvGRU的收敛速度比 ConvLSTM快约25%. ConvLSTM和ConvGRU的预警性能随地区, 时间, 降雨强度的变化趋势相似, 但大部分ConvLSTM的得分较高, 少数情况下ConvGRU的得分较高.

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
Atmospheric and Oceanic Science Letters
Atmospheric and Oceanic Science Letters METEOROLOGY & ATMOSPHERIC SCIENCES-
CiteScore
4.20
自引率
8.70%
发文量
925
审稿时长
12 weeks
期刊最新文献
Implications of the extremely hot summer of 2022 on urban ozone control in China Impacts of global biogenic isoprene emissions on surface ozone during 2000–2019 Enhanced nitrous acid (HONO) formation via NO2 uptake and its potential contribution to heavy haze formation during wintertime A portable instrument for measurement of atmospheric Ox and NO2 based on cavity ring-down spectroscopy Vertical distributions of VOCs in the Tibetan Plateau background region
×
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