PROBABILISTIC SHORT TERM SOLAR DRIVER FORECASTING WITH NEURAL NETWORK ENSEMBLES

IF 3.7 2区 地球科学 Space Weather Pub Date : 2024-03-01 DOI:10.33915/etd.12262
Joshua D. Daniell, P. Mehta
{"title":"PROBABILISTIC SHORT TERM SOLAR DRIVER FORECASTING WITH NEURAL NETWORK ENSEMBLES","authors":"Joshua D. Daniell, P. Mehta","doi":"10.33915/etd.12262","DOIUrl":null,"url":null,"abstract":"Space weather indices are used to drive forecasts of thermosphere density, which directly affects objects in low‐Earth orbit (LEO) through atmospheric drag force. A set of proxies and indices (drivers), F10.7, S10.7, M10.7, and Y10.7 are used as inputs by the JB2008, (https://doi.org/10.2514/6.2008‐6438) thermosphere density model. The United States Air Force (USAF) operational High Accuracy Satellite Drag Model (HASDM), relies on JB2008, (https://doi.org/10.2514/6.2008‐6438), and forecasts of solar drivers from a linear algorithm. We introduce methods using long short‐term memory (LSTM) model ensembles to improve over the current prediction method as well as a previous univariate approach. We investigate the usage of principal component analysis (PCA) to enhance multivariate forecasting. A novel method, referred to as striped sampling, is created to produce statistically consistent machine learning data sets. We also investigate forecasting performance and uncertainty estimation by varying the training loss function and by investigating novel weighting methods. Results show that stacked neural network model ensembles make multivariate driver forecasts which outperform the operational linear method. When using MV‐MLE (multivariate multi‐lookback ensemble), we see an improvement of RMSE for F10.7, S10.7, M10.7, and Y10.7 of 17.7%, 12.3%, 13.8%, 13.7% respectively, over the operational method. We provide the first probabilistic forecasting method for S10.7, M10.7, and Y10.7. Ensemble approaches are leveraged to provide a distribution of predicted values, allowing an investigation into robustness and reliability (R&R) of uncertainty estimates. Uncertainty was also investigated through the use of calibration error score (CES), with the MV‐MLE providing an average CES of 5.63%, across all drivers.","PeriodicalId":22181,"journal":{"name":"Space Weather","volume":null,"pages":null},"PeriodicalIF":3.7000,"publicationDate":"2024-03-01","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/10.33915/etd.12262","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

Abstract

Space weather indices are used to drive forecasts of thermosphere density, which directly affects objects in low‐Earth orbit (LEO) through atmospheric drag force. A set of proxies and indices (drivers), F10.7, S10.7, M10.7, and Y10.7 are used as inputs by the JB2008, (https://doi.org/10.2514/6.2008‐6438) thermosphere density model. The United States Air Force (USAF) operational High Accuracy Satellite Drag Model (HASDM), relies on JB2008, (https://doi.org/10.2514/6.2008‐6438), and forecasts of solar drivers from a linear algorithm. We introduce methods using long short‐term memory (LSTM) model ensembles to improve over the current prediction method as well as a previous univariate approach. We investigate the usage of principal component analysis (PCA) to enhance multivariate forecasting. A novel method, referred to as striped sampling, is created to produce statistically consistent machine learning data sets. We also investigate forecasting performance and uncertainty estimation by varying the training loss function and by investigating novel weighting methods. Results show that stacked neural network model ensembles make multivariate driver forecasts which outperform the operational linear method. When using MV‐MLE (multivariate multi‐lookback ensemble), we see an improvement of RMSE for F10.7, S10.7, M10.7, and Y10.7 of 17.7%, 12.3%, 13.8%, 13.7% respectively, over the operational method. We provide the first probabilistic forecasting method for S10.7, M10.7, and Y10.7. Ensemble approaches are leveraged to provide a distribution of predicted values, allowing an investigation into robustness and reliability (R&R) of uncertainty estimates. Uncertainty was also investigated through the use of calibration error score (CES), with the MV‐MLE providing an average CES of 5.63%, across all drivers.
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
利用神经网络集合进行短期太阳驱动力概率预测
空间气象指数用于驱动热层密度的预测,热层密度通过大气阻力直接影响低地轨道(LEO)上的物体。JB2008(https://doi.org/10.2514/6.2008-6438)热大气层密度模型使用一套代用指标和指数(驱动因素)F10.7、S10.7、M10.7和Y10.7作为输入。美国空军(USAF)运行的高精度卫星阻力模型(HASDM)依赖于 JB2008, (https://doi.org/10.2514/6.2008-6438) 和线性算法对太阳驱动因素的预测。我们引入了使用长短期记忆(LSTM)模型集合的方法,以改进当前的预测方法和以前的单变量方法。我们研究了如何利用主成分分析(PCA)来加强多变量预测。我们创建了一种称为条带采样的新方法,用于生成统计上一致的机器学习数据集。我们还通过改变训练损失函数和研究新型加权方法,对预测性能和不确定性估计进行了研究。结果表明,堆叠神经网络模型集合的多变量驱动预测效果优于操作线性方法。当使用 MV-MLE(多变量多回看集合)时,我们发现 F10.7、S10.7、M10.7 和 Y10.7 的均方根误差(RMSE)比运算法分别提高了 17.7%、12.3%、13.8% 和 13.7%。我们首次为 S10.7、M10.7 和 Y10.7 提供了概率预测方法。利用集合方法提供了预测值的分布,从而对不确定性估计的稳健性和可靠性(R&R)进行了研究。还通过使用校准误差分(CES)对不确定性进行了研究,MV-MLE 为所有驱动因素提供了 5.63% 的平均 CES。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
29.70%
发文量
166
期刊最新文献
Quantification of Representation Error in the Neutral Winds and Ion Drifts Using Data Assimilation A Novel Ionospheric Inversion Model: PINN-SAMI3 (Physics Informed Neural Network Based on SAMI3) Nowcasting Solar EUV Irradiance With Photospheric Magnetic Fields and the Mg II Index Calculating the High-Latitude Ionospheric Electrodynamics Using a Machine Learning-Based Field-Aligned Current Model Effects of Forbush Decreases on the Global Electric Circuit
×
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