利用卷积神经网络对零星 E 进行检测和分类

IF 3.7 2区 地球科学
Space Weather Pub Date : 2024-01-12 DOI:10.1029/2023sw003669
J. A. Ellis, D. J. Emmons, M. B. Cohen
{"title":"利用卷积神经网络对零星 E 进行检测和分类","authors":"J. A. Ellis, D. J. Emmons, M. B. Cohen","doi":"10.1029/2023sw003669","DOIUrl":null,"url":null,"abstract":"In this work, convolutional neural networks (CNN) are developed to detect and characterize sporadic E (<i>E</i><sub><i>s</i></sub>), demonstrating an improvement over current methods. This includes a binary classification model to determine if <i>E</i><sub><i>s</i></sub> is present, followed by a regression model to estimate the <i>E</i><sub><i>s</i></sub> ordinary mode critical frequency (foEs), a proxy for the intensity, along with the height at which the <i>E</i><sub><i>s</i></sub> layer occurs (hEs). Signal-to-noise ratio (SNR) and excess phase profiles from six Global Navigation Satellite System (GNSS) radio occultation (RO) missions during the years 2008–2022 are used as the inputs of the model. Intensity (foEs) and the height (hEs) values are obtained from the global network of ground-based Digisonde ionosondes and are used as the “ground truth,” or target variables, during training. After corresponding the two data sets, a total of 36,521 samples are available for training and testing the models. The foEs CNN binary classification model achieved an accuracy of 74% and F1-score of 0.70. Mean absolute errors (MAE) of 0.63 MHz and 5.81 km along with root-mean squared errors (RMSE) of 0.95 MHz and 7.89 km were attained for estimating foEs and hEs, respectively, when it was known that <i>E</i><sub><i>s</i></sub> was present. When combining the classification and regression models together for use in practical applications where it is unknown if <i>E</i><sub><i>s</i></sub> is present, an foEs MAE and RMSE of 0.97 and 1.65 MHz, respectively, were realized. We implemented three other techniques for sporadic E characterization, and found that the CNN model appears to perform better.","PeriodicalId":22181,"journal":{"name":"Space Weather","volume":null,"pages":null},"PeriodicalIF":3.7000,"publicationDate":"2024-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Detection and Classification of Sporadic E Using Convolutional Neural Networks\",\"authors\":\"J. A. Ellis, D. J. Emmons, M. B. Cohen\",\"doi\":\"10.1029/2023sw003669\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work, convolutional neural networks (CNN) are developed to detect and characterize sporadic E (<i>E</i><sub><i>s</i></sub>), demonstrating an improvement over current methods. This includes a binary classification model to determine if <i>E</i><sub><i>s</i></sub> is present, followed by a regression model to estimate the <i>E</i><sub><i>s</i></sub> ordinary mode critical frequency (foEs), a proxy for the intensity, along with the height at which the <i>E</i><sub><i>s</i></sub> layer occurs (hEs). Signal-to-noise ratio (SNR) and excess phase profiles from six Global Navigation Satellite System (GNSS) radio occultation (RO) missions during the years 2008–2022 are used as the inputs of the model. Intensity (foEs) and the height (hEs) values are obtained from the global network of ground-based Digisonde ionosondes and are used as the “ground truth,” or target variables, during training. After corresponding the two data sets, a total of 36,521 samples are available for training and testing the models. The foEs CNN binary classification model achieved an accuracy of 74% and F1-score of 0.70. Mean absolute errors (MAE) of 0.63 MHz and 5.81 km along with root-mean squared errors (RMSE) of 0.95 MHz and 7.89 km were attained for estimating foEs and hEs, respectively, when it was known that <i>E</i><sub><i>s</i></sub> was present. When combining the classification and regression models together for use in practical applications where it is unknown if <i>E</i><sub><i>s</i></sub> is present, an foEs MAE and RMSE of 0.97 and 1.65 MHz, respectively, were realized. We implemented three other techniques for sporadic E characterization, and found that the CNN model appears to perform better.\",\"PeriodicalId\":22181,\"journal\":{\"name\":\"Space Weather\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.7000,\"publicationDate\":\"2024-01-12\",\"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/10.1029/2023sw003669\",\"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/10.1029/2023sw003669","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

本研究开发了卷积神经网络 (CNN) 来检测和描述零星 E(Es),显示了对现有方法的改进。这包括一个二元分类模型,用于确定是否存在Es,然后是一个回归模型,用于估算Es的普通模式临界频率(foEs)(强度的替代物)以及Es层出现的高度(hEs)。信噪比(SNR)和来自 2008-2022 年期间六次全球导航卫星系统(GNSS)无线电掩星任务的过量相位剖面图被用作模型的输入。强度(foEs)和高度(hEs)值来自全球地面 Digisonde 电离层探测仪网络,在训练过程中用作 "地面实况 "或目标变量。两组数据对应后,共有 36521 个样本可用于训练和测试模型。foEs CNN 二元分类模型的准确率达到 74%,F1 分数为 0.70。在已知存在 Es 的情况下,估计 foEs 和 hEs 的平均绝对误差(MAE)分别为 0.63 MHz 和 5.81 km,均方根误差(RMSE)分别为 0.95 MHz 和 7.89 km。当把分类和回归模型结合在一起用于未知是否存在 Es 的实际应用时,foEs MAE 和 RMSE 分别为 0.97 和 1.65 MHz。我们采用了其他三种技术来鉴定零星 E,发现 CNN 模型的性能似乎更好。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Detection and Classification of Sporadic E Using Convolutional Neural Networks
In this work, convolutional neural networks (CNN) are developed to detect and characterize sporadic E (Es), demonstrating an improvement over current methods. This includes a binary classification model to determine if Es is present, followed by a regression model to estimate the Es ordinary mode critical frequency (foEs), a proxy for the intensity, along with the height at which the Es layer occurs (hEs). Signal-to-noise ratio (SNR) and excess phase profiles from six Global Navigation Satellite System (GNSS) radio occultation (RO) missions during the years 2008–2022 are used as the inputs of the model. Intensity (foEs) and the height (hEs) values are obtained from the global network of ground-based Digisonde ionosondes and are used as the “ground truth,” or target variables, during training. After corresponding the two data sets, a total of 36,521 samples are available for training and testing the models. The foEs CNN binary classification model achieved an accuracy of 74% and F1-score of 0.70. Mean absolute errors (MAE) of 0.63 MHz and 5.81 km along with root-mean squared errors (RMSE) of 0.95 MHz and 7.89 km were attained for estimating foEs and hEs, respectively, when it was known that Es was present. When combining the classification and regression models together for use in practical applications where it is unknown if Es is present, an foEs MAE and RMSE of 0.97 and 1.65 MHz, respectively, were realized. We implemented three other techniques for sporadic E characterization, and found that the CNN model appears to perform better.
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