F10.7 使用 LSTM 结合 VMD 方法进行每日预测

IF 3.7 2区 地球科学
Space Weather Pub Date : 2024-01-17 DOI:10.1029/2023sw003552
Yuhang Hao, Jianyong Lu, Guangshuai Peng, Ming Wang, Jingyuan Li, Guanchun Wei
{"title":"F10.7 使用 LSTM 结合 VMD 方法进行每日预测","authors":"Yuhang Hao, Jianyong Lu, Guangshuai Peng, Ming Wang, Jingyuan Li, Guanchun Wei","doi":"10.1029/2023sw003552","DOIUrl":null,"url":null,"abstract":"The <i>F</i><sub>10.7</sub> solar radiation flux is a well-known parameter that is closely linked to solar activity, serving as a key index for measuring the level of solar activity. In this study, the Variational Mode Decomposition (VMD) and Long Short-term Memory (LSTM) network are combined to construct a VMD-LSTM model for predicting <i>F</i><sub>10.7</sub> values. The <i>F</i><sub>10.7</sub> sequence is decomposed into several intrinsic mode functions (IMF) by VMD, then the LSTM neural network is utilized to forecast each IMF. All IMF prediction results are aggregated to obtain the final <i>F</i><sub>10.7</sub> value. The data sets from 1957 to 2008 are used for training and the data sets from 2009 to 2019 are used for testing. The results show that the VMD-LSTM model achieves an annual average root mean square error of only 4.47 sfu and an annual average correlation coefficient (<i>R</i>) of 0.99 during solar cycle 24, which is significantly better than the accuracy of the LSTM model (W. Zhang et al., 2022, https://doi.org/10.3390/universe8010030), the AR model (Du, 2020, https://doi.org/10.1007/s11207-020-01689-x), and the BP model (Xiao et al., 2017, https://doi.org/10.11728/cjss2017.01.001). The VMD-LSTM model exhibits strong predictive capability for the <i>F</i><sub>10.7</sub> index during solar cycle 24.","PeriodicalId":22181,"journal":{"name":"Space Weather","volume":null,"pages":null},"PeriodicalIF":3.7000,"publicationDate":"2024-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"F10.7 Daily Forecast Using LSTM Combined With VMD Method\",\"authors\":\"Yuhang Hao, Jianyong Lu, Guangshuai Peng, Ming Wang, Jingyuan Li, Guanchun Wei\",\"doi\":\"10.1029/2023sw003552\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The <i>F</i><sub>10.7</sub> solar radiation flux is a well-known parameter that is closely linked to solar activity, serving as a key index for measuring the level of solar activity. In this study, the Variational Mode Decomposition (VMD) and Long Short-term Memory (LSTM) network are combined to construct a VMD-LSTM model for predicting <i>F</i><sub>10.7</sub> values. The <i>F</i><sub>10.7</sub> sequence is decomposed into several intrinsic mode functions (IMF) by VMD, then the LSTM neural network is utilized to forecast each IMF. All IMF prediction results are aggregated to obtain the final <i>F</i><sub>10.7</sub> value. The data sets from 1957 to 2008 are used for training and the data sets from 2009 to 2019 are used for testing. The results show that the VMD-LSTM model achieves an annual average root mean square error of only 4.47 sfu and an annual average correlation coefficient (<i>R</i>) of 0.99 during solar cycle 24, which is significantly better than the accuracy of the LSTM model (W. Zhang et al., 2022, https://doi.org/10.3390/universe8010030), the AR model (Du, 2020, https://doi.org/10.1007/s11207-020-01689-x), and the BP model (Xiao et al., 2017, https://doi.org/10.11728/cjss2017.01.001). The VMD-LSTM model exhibits strong predictive capability for the <i>F</i><sub>10.7</sub> index during solar cycle 24.\",\"PeriodicalId\":22181,\"journal\":{\"name\":\"Space Weather\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.7000,\"publicationDate\":\"2024-01-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Space Weather\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1029/2023sw003552\",\"RegionNum\":2,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Space Weather","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1029/2023sw003552","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

众所周知,F10.7 太阳辐射通量是一个与太阳活动密切相关的参数,是衡量太阳活动水平的关键指标。本研究将变异模式分解(VMD)和长短期记忆(LSTM)网络相结合,构建了预测 F10.7 值的 VMD-LSTM 模型。VMD 将 F10.7 序列分解为多个固有模式函数 (IMF),然后利用 LSTM 神经网络预测每个 IMF。所有 IMF 预测结果汇总后得到最终的 F10.7 值。1957 年至 2008 年的数据集用于训练,2009 年至 2019 年的数据集用于测试。结果表明,VMD-LSTM 模型在太阳周期 24 期间的年均均方根误差仅为 4.47 sfu,年均相关系数(R)为 0.99,明显优于 LSTM 模型(W. Zhang 等,2022,https://doi.org/10.3390/universe8010030)、AR 模型(Du,2020,https://doi.org/10.1007/s11207-020-01689-x)和 BP 模型(Xiao 等,2017,https://doi.org/10.11728/cjss2017.01.001)的精度。VMD-LSTM模型对太阳周期24期间的F10.7指数具有很强的预测能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
F10.7 Daily Forecast Using LSTM Combined With VMD Method
The F10.7 solar radiation flux is a well-known parameter that is closely linked to solar activity, serving as a key index for measuring the level of solar activity. In this study, the Variational Mode Decomposition (VMD) and Long Short-term Memory (LSTM) network are combined to construct a VMD-LSTM model for predicting F10.7 values. The F10.7 sequence is decomposed into several intrinsic mode functions (IMF) by VMD, then the LSTM neural network is utilized to forecast each IMF. All IMF prediction results are aggregated to obtain the final F10.7 value. The data sets from 1957 to 2008 are used for training and the data sets from 2009 to 2019 are used for testing. The results show that the VMD-LSTM model achieves an annual average root mean square error of only 4.47 sfu and an annual average correlation coefficient (R) of 0.99 during solar cycle 24, which is significantly better than the accuracy of the LSTM model (W. Zhang et al., 2022, https://doi.org/10.3390/universe8010030), the AR model (Du, 2020, https://doi.org/10.1007/s11207-020-01689-x), and the BP model (Xiao et al., 2017, https://doi.org/10.11728/cjss2017.01.001). The VMD-LSTM model exhibits strong predictive capability for the F10.7 index during solar cycle 24.
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
29.70%
发文量
166
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信