Using Classification Methods in Forecasting the Level of Geomagnetic Field Disturbance Based on the Kp-Index

IF 0.7 4区 地球科学 Q4 GEOCHEMISTRY & GEOPHYSICS
I. M. Gadzhiev, O. G. Barinov, I. N. Myagkova, S. A. Dolenko
{"title":"Using Classification Methods in Forecasting the Level of Geomagnetic Field Disturbance Based on the Kp-Index","authors":"I. M. Gadzhiev,&nbsp;O. G. Barinov,&nbsp;I. N. Myagkova,&nbsp;S. A. Dolenko","doi":"10.1134/S0016793224600140","DOIUrl":null,"url":null,"abstract":"<p>The paper explores the possibilities of using data classification methods when forecasting time series of the geomagnetic <i>Kp</i>-index by machine learning methods. To classify categories of the <i>Kp</i>-index based on the degree of disturbance, linear and logistic regression, random forest, gradient boosting on top of decision trees, and artificial neural networks of various architectures are used. The results of these methods are compared with a trivial inertial forecast (the statistical indicators of which for problems of this type are always high) at horizons from 3 h to 1 day in 3-h increments. The problem of choosing a cross-validation scheme for selecting the model hyperparameters, ways to overcome the imbalance of categories, the relative importance of input features, as well as the dependence of the results on the test sample (beginning of the 25th solar activity cycle) on inclusion in the training sample of data from the 23rd and 24th cycles or only the 24th cycles are studied. Based on the results, conclusions are drawn about the preferred methods for classifying values of the <i>Kp</i>-index based on the level of geomagnetic disturbance. Ways for further research and possible improvement of the classification quality are outlined, including for determining the characteristic hidden states of Earth’s magnetosphere as a dynamic system in order to improve the quality of forecasting geomagnetic indices.</p>","PeriodicalId":55597,"journal":{"name":"Geomagnetism and Aeronomy","volume":null,"pages":null},"PeriodicalIF":0.7000,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geomagnetism and Aeronomy","FirstCategoryId":"89","ListUrlMain":"https://link.springer.com/article/10.1134/S0016793224600140","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"GEOCHEMISTRY & GEOPHYSICS","Score":null,"Total":0}
引用次数: 0

Abstract

The paper explores the possibilities of using data classification methods when forecasting time series of the geomagnetic Kp-index by machine learning methods. To classify categories of the Kp-index based on the degree of disturbance, linear and logistic regression, random forest, gradient boosting on top of decision trees, and artificial neural networks of various architectures are used. The results of these methods are compared with a trivial inertial forecast (the statistical indicators of which for problems of this type are always high) at horizons from 3 h to 1 day in 3-h increments. The problem of choosing a cross-validation scheme for selecting the model hyperparameters, ways to overcome the imbalance of categories, the relative importance of input features, as well as the dependence of the results on the test sample (beginning of the 25th solar activity cycle) on inclusion in the training sample of data from the 23rd and 24th cycles or only the 24th cycles are studied. Based on the results, conclusions are drawn about the preferred methods for classifying values of the Kp-index based on the level of geomagnetic disturbance. Ways for further research and possible improvement of the classification quality are outlined, including for determining the characteristic hidden states of Earth’s magnetosphere as a dynamic system in order to improve the quality of forecasting geomagnetic indices.

Abstract Image

Abstract Image

根据 Kp 指数使用分类方法预测地磁场扰动程度
摘要 本文探讨了用机器学习方法预测地磁 Kp 指数时间序列时使用数据分类方法的可能性。为了根据干扰程度对 Kp 指数进行分类,使用了线性和逻辑回归、随机森林、决策树之上的梯度提升以及各种架构的人工神经网络。将这些方法的结果与三维惯性预报(此类问题的统计指标总是很高)进行比较,预报时间范围从 3 小时到 1 天,每 3 小时为一个增量。研究了选择模型超参数的交叉验证方案、克服类别不平衡的方法、输入特征的相对重要性,以及测试样本(第 25 个太阳活动周期的开始)的结果对训练样本中包含第 23 和 24 个周期或仅包含第 24 个周期数据的依赖性。根据研究结果,得出了根据地磁干扰程度对 Kp 指数值进行分类的首选方法。概述了进一步研究和可能提高分类质量的方法,包括确定地球磁层作为动态系统的特征隐藏状态,以提高地磁指数预报的质量。
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
Geomagnetism and Aeronomy
Geomagnetism and Aeronomy Earth and Planetary Sciences-Space and Planetary Science
CiteScore
1.30
自引率
33.30%
发文量
65
审稿时长
4-8 weeks
期刊介绍: Geomagnetism and Aeronomy is a bimonthly periodical that covers the fields of interplanetary space; geoeffective solar events; the magnetosphere; the ionosphere; the upper and middle atmosphere; the action of solar variability and activity on atmospheric parameters and climate; the main magnetic field and its secular variations, excursion, and inversion; and other related topics.
×
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