Synthesis‐Style Auto‐Correlation‐Based Transformer: A Learner on Ionospheric TEC Series Forecasting

IF 3.8 2区 地球科学 Q2 ASTRONOMY & ASTROPHYSICS
Yuhuan Yuan, Guozhen Xia, Xinmiao Zhang, Chen Zhou
{"title":"Synthesis‐Style Auto‐Correlation‐Based Transformer: A Learner on Ionospheric TEC Series Forecasting","authors":"Yuhuan Yuan, Guozhen Xia, Xinmiao Zhang, Chen Zhou","doi":"10.1029/2023sw003472","DOIUrl":null,"url":null,"abstract":"Abstract Accurate 1‐day global total electron content (TEC) forecasting is essential for ionospheric monitoring and satellite communications. However, it faces challenges due to limited data and difficulty in modeling long‐term dependencies. This study develops a highly accurate model for 1‐day global TEC forecasting. We utilized generative TEC data augmentation based on the International Global Navigation Satellite Service (IGS) data set from 1998 to 2017 to enhance the model's prediction ability. Our model takes the TEC sequence of the previous 2 days as input and predicts the global TEC value for each hourly step of the next day. We compared the performance of our model with 1‐day predicted ionospheric products provided by both the Center for Orbit Determination in Europe (C1PG) and Beihang University (B1PG). We proposed a two‐step framework: (a) a time series generative model to produce realistic synthetic TEC data for training, and (b) an auto‐correlation‐based transformer model designed to capture long‐range dependencies in the TEC sequence. Experiments demonstrate that our model significantly improves 1‐day forecast accuracy over prior approaches. On the 2018 benchmark data set, the global root mean squared error (RMSE) of our model is reduced to 1.17 TEC units (TECU), while the RMSE of the C1PG model is 2.07 TECU. Reliability is higher in middle and high latitudes but lower in low latitudes (RMSE < 2.5 TECU), indicating room for improvement. This study highlights the potential of using data augmentation and auto‐correlation‐based transformer models trained on synthetic data to achieve high‐quality 1‐day global TEC forecasting.","PeriodicalId":49487,"journal":{"name":"Space Weather-The International Journal of Research and Applications","volume":null,"pages":null},"PeriodicalIF":3.8000,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Space Weather-The International Journal of Research and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1029/2023sw003472","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ASTRONOMY & ASTROPHYSICS","Score":null,"Total":0}
引用次数: 0

Abstract

Abstract Accurate 1‐day global total electron content (TEC) forecasting is essential for ionospheric monitoring and satellite communications. However, it faces challenges due to limited data and difficulty in modeling long‐term dependencies. This study develops a highly accurate model for 1‐day global TEC forecasting. We utilized generative TEC data augmentation based on the International Global Navigation Satellite Service (IGS) data set from 1998 to 2017 to enhance the model's prediction ability. Our model takes the TEC sequence of the previous 2 days as input and predicts the global TEC value for each hourly step of the next day. We compared the performance of our model with 1‐day predicted ionospheric products provided by both the Center for Orbit Determination in Europe (C1PG) and Beihang University (B1PG). We proposed a two‐step framework: (a) a time series generative model to produce realistic synthetic TEC data for training, and (b) an auto‐correlation‐based transformer model designed to capture long‐range dependencies in the TEC sequence. Experiments demonstrate that our model significantly improves 1‐day forecast accuracy over prior approaches. On the 2018 benchmark data set, the global root mean squared error (RMSE) of our model is reduced to 1.17 TEC units (TECU), while the RMSE of the C1PG model is 2.07 TECU. Reliability is higher in middle and high latitudes but lower in low latitudes (RMSE < 2.5 TECU), indicating room for improvement. This study highlights the potential of using data augmentation and auto‐correlation‐based transformer models trained on synthetic data to achieve high‐quality 1‐day global TEC forecasting.
基于综合型自相关的变压器:电离层TEC系列预测的学习器
准确的1天全球总电子含量(TEC)预报对于电离层监测和卫星通信至关重要。然而,由于数据有限和长期依赖关系建模困难,它面临着挑战。本研究开发了一个高精度的1天全球TEC预测模型。利用1998 - 2017年国际全球导航卫星服务(IGS)数据集进行生成式TEC数据增强,增强模型的预测能力。我们的模型以前2天的TEC序列作为输入,并预测第二天每小时的全球TEC值。我们将模型的性能与欧洲轨道测定中心(C1PG)和北京航空航天大学(B1PG)提供的1天电离层预测产品进行了比较。我们提出了一个两步框架:(a)一个时间序列生成模型,用于生成真实的综合TEC数据用于训练;(b)一个基于自相关的变压器模型,用于捕获TEC序列中的长期依赖关系。实验表明,我们的模型比以前的方法显著提高了1天的预测精度。在2018年的基准数据集上,我们的模型的全局均方根误差(RMSE)降至1.17 TEC单位(TECU),而C1PG模型的RMSE为2.07 TECU。信度在中高纬度地区较高,在低纬度地区较低(RMSE <2.5 TECU),表明有改进的余地。这项研究强调了使用数据增强和基于自相关的变压器模型的潜力,这些模型经过综合数据的训练,可以实现高质量的1天全球TEC预测。
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 求助全文
来源期刊
CiteScore
5.90
自引率
29.70%
发文量
166
审稿时长
>12 weeks
期刊介绍: Space Weather: The International Journal of Research and Applications (SWE) is devoted to understanding and forecasting space weather. The scope of understanding and forecasting includes: origins, propagation and interactions of solar-produced processes within geospace; interactions in Earth’s space-atmosphere interface region produced by disturbances from above and below; influences of cosmic rays on humans, hardware, and signals; and comparisons of these types of interactions and influences with the atmospheres of neighboring planets and Earth’s moon. Manuscripts should emphasize impacts on technical systems including telecommunications, transportation, electric power, satellite navigation, avionics/spacecraft design and operations, human spaceflight, and other systems. Manuscripts that describe models or space environment climatology should clearly state how the results can be applied.
×
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