A Novel Model for Forecasting Geomagnetic Indices Using Machine Learning

Abstract Widely used geomagnetic activity indices like Kp or Dst, derived from the combined data from several observatories distributed worldwide, are crucial to forecasting since solar‐driven geomagnetic activity can significantly affect technology and human activities on Earth and in near‐Earth sp...

Full description

Saved in:
Bibliographic Details
Main Authors: Guram Kervalishvili, Ingo Michaelis, Monika Korte, Jan Rauberg, Jürgen Matzka
Format: Article
Language:English
Published: Wiley 2025-04-01
Series:Geophysical Research Letters
Subjects:
Online Access:https://doi.org/10.1029/2025GL114848
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850038509152239616
author Guram Kervalishvili
Ingo Michaelis
Monika Korte
Jan Rauberg
Jürgen Matzka
author_facet Guram Kervalishvili
Ingo Michaelis
Monika Korte
Jan Rauberg
Jürgen Matzka
author_sort Guram Kervalishvili
collection DOAJ
description Abstract Widely used geomagnetic activity indices like Kp or Dst, derived from the combined data from several observatories distributed worldwide, are crucial to forecasting since solar‐driven geomagnetic activity can significantly affect technology and human activities on Earth and in near‐Earth space. We developed a new model to forecast geomagnetic indices by incorporating predicted data from individual observatories. Unlike previous models that rely solely on an index and overlook local physical effects, our approach accounts for each observatory separately in the forecasting process, allowing for index predictions that integrate the same physical principles as in the original calculations of the index. We demonstrate the model's performance for Kp and the newer Hpo indices (Hp60 and Hp30), which measure planetary disturbances with higher resolution than Kp and without its upper limit of 9. The model demonstrates good agreement, accurately capturing trends and overall behavior, even with sparse solar wind data.
format Article
id doaj-art-fa427d3c952f4a1abc5d082e5333f9de
institution DOAJ
issn 0094-8276
1944-8007
language English
publishDate 2025-04-01
publisher Wiley
record_format Article
series Geophysical Research Letters
spelling doaj-art-fa427d3c952f4a1abc5d082e5333f9de2025-08-20T02:56:35ZengWileyGeophysical Research Letters0094-82761944-80072025-04-01528n/an/a10.1029/2025GL114848A Novel Model for Forecasting Geomagnetic Indices Using Machine LearningGuram Kervalishvili0Ingo Michaelis1Monika Korte2Jan Rauberg3Jürgen Matzka4GFZ Helmholtz Centre for Geosciences Potsdam GermanyGFZ Helmholtz Centre for Geosciences Potsdam GermanyGFZ Helmholtz Centre for Geosciences Potsdam GermanyGFZ Helmholtz Centre for Geosciences Potsdam GermanyGFZ Helmholtz Centre for Geosciences Potsdam GermanyAbstract Widely used geomagnetic activity indices like Kp or Dst, derived from the combined data from several observatories distributed worldwide, are crucial to forecasting since solar‐driven geomagnetic activity can significantly affect technology and human activities on Earth and in near‐Earth space. We developed a new model to forecast geomagnetic indices by incorporating predicted data from individual observatories. Unlike previous models that rely solely on an index and overlook local physical effects, our approach accounts for each observatory separately in the forecasting process, allowing for index predictions that integrate the same physical principles as in the original calculations of the index. We demonstrate the model's performance for Kp and the newer Hpo indices (Hp60 and Hp30), which measure planetary disturbances with higher resolution than Kp and without its upper limit of 9. The model demonstrates good agreement, accurately capturing trends and overall behavior, even with sparse solar wind data.https://doi.org/10.1029/2025GL114848Kp indexHpo indicesHp30 indexsolar windforecastgeomagnetic activity
spellingShingle Guram Kervalishvili
Ingo Michaelis
Monika Korte
Jan Rauberg
Jürgen Matzka
A Novel Model for Forecasting Geomagnetic Indices Using Machine Learning
Geophysical Research Letters
Kp index
Hpo indices
Hp30 index
solar wind
forecast
geomagnetic activity
title A Novel Model for Forecasting Geomagnetic Indices Using Machine Learning
title_full A Novel Model for Forecasting Geomagnetic Indices Using Machine Learning
title_fullStr A Novel Model for Forecasting Geomagnetic Indices Using Machine Learning
title_full_unstemmed A Novel Model for Forecasting Geomagnetic Indices Using Machine Learning
title_short A Novel Model for Forecasting Geomagnetic Indices Using Machine Learning
title_sort novel model for forecasting geomagnetic indices using machine learning
topic Kp index
Hpo indices
Hp30 index
solar wind
forecast
geomagnetic activity
url https://doi.org/10.1029/2025GL114848
work_keys_str_mv AT guramkervalishvili anovelmodelforforecastinggeomagneticindicesusingmachinelearning
AT ingomichaelis anovelmodelforforecastinggeomagneticindicesusingmachinelearning
AT monikakorte anovelmodelforforecastinggeomagneticindicesusingmachinelearning
AT janrauberg anovelmodelforforecastinggeomagneticindicesusingmachinelearning
AT jurgenmatzka anovelmodelforforecastinggeomagneticindicesusingmachinelearning
AT guramkervalishvili novelmodelforforecastinggeomagneticindicesusingmachinelearning
AT ingomichaelis novelmodelforforecastinggeomagneticindicesusingmachinelearning
AT monikakorte novelmodelforforecastinggeomagneticindicesusingmachinelearning
AT janrauberg novelmodelforforecastinggeomagneticindicesusingmachinelearning
AT jurgenmatzka novelmodelforforecastinggeomagneticindicesusingmachinelearning