A Novel Neural Network‐Based Approach to Derive a Local Geomagnetic Baseline for Future Robust Characterization of Geomagnetic Indices at Mid‐Latitude

Abstract Geomagnetic indices derived from ground magnetic measurements characterize the intensity of solar‐terrestrial interaction. Global magnetic indices derived from multiple magnetic observatories at mid‐latitude have commonly been used for space weather operations. Yet, their temporal cadence i...

Full description

Saved in:
Bibliographic Details
Main Authors: Rungployphan Kieokaew, Veronika Haberle, Aurélie Marchaudon, Pierre‐Louis Blelly, Aude Chambodut
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Space Weather
Subjects:
Online Access:https://doi.org/10.1029/2024SW004192
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850277674644144128
author Rungployphan Kieokaew
Veronika Haberle
Aurélie Marchaudon
Pierre‐Louis Blelly
Aude Chambodut
author_facet Rungployphan Kieokaew
Veronika Haberle
Aurélie Marchaudon
Pierre‐Louis Blelly
Aude Chambodut
author_sort Rungployphan Kieokaew
collection DOAJ
description Abstract Geomagnetic indices derived from ground magnetic measurements characterize the intensity of solar‐terrestrial interaction. Global magnetic indices derived from multiple magnetic observatories at mid‐latitude have commonly been used for space weather operations. Yet, their temporal cadence is low and their intensity scale is crude. To derive a new generation of geomagnetic indices, it is desirable to establish a geomagnetic baseline that defines the quiet‐level of activity without solar‐driven perturbations. We present a new approach for deriving a baseline that represents the time‐dependent quiet variations focusing on data from Chambon‐la‐Forêt, France. Using a filtering technique, the measurements are first decomposed into the above‐diurnal (>24 hr) variation and the sum of 24, 12, 8, and 6 hr filters, called the daily variation. Using parameters that correlate with the ionospheric solar‐quiet (Sq) currents, we predict the daily “quiet” variation that excludes the effects of solar‐transient perturbations. Here, we train long short‐term memory neural networks using at least 11 years of data at 1 hr cadence. This predicted daily quiet variation is combined with linear extrapolation of the secular trend associated with the intrinsic geomagnetic variability, which dominates the above‐diurnal variation, to yield a local geomagnetic baseline. Unlike the existing baselines, our baseline is insensitive to geomagnetic storms. It is thus suitable for future definitions of geomagnetic indices that accurately reflect the intensity of solar‐driven perturbations. Our methodology is quick to implement and scalable, making it suitable for real‐time operation. Strategies for operational forecasting of our geomagnetic baseline 1 day and 27 days in advance are presented.
format Article
id doaj-art-ab4d840f79d644d3ba84e64dde48179b
institution OA Journals
issn 1542-7390
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Space Weather
spelling doaj-art-ab4d840f79d644d3ba84e64dde48179b2025-08-20T01:49:47ZengWileySpace Weather1542-73902025-03-01233n/an/a10.1029/2024SW004192A Novel Neural Network‐Based Approach to Derive a Local Geomagnetic Baseline for Future Robust Characterization of Geomagnetic Indices at Mid‐LatitudeRungployphan Kieokaew0Veronika Haberle1Aurélie Marchaudon2Pierre‐Louis Blelly3Aude Chambodut4Institut de Recherche en Astrophysique et Planétologie CNRS CNES Université de Toulouse Toulouse FranceInstitut de Recherche en Astrophysique et Planétologie CNRS CNES Université de Toulouse Toulouse FranceInstitut de Recherche en Astrophysique et Planétologie CNRS CNES Université de Toulouse Toulouse FranceInstitut de Recherche en Astrophysique et Planétologie CNRS CNES Université de Toulouse Toulouse FranceCNRS ITES Université de Strasbourg Strasbourg FranceAbstract Geomagnetic indices derived from ground magnetic measurements characterize the intensity of solar‐terrestrial interaction. Global magnetic indices derived from multiple magnetic observatories at mid‐latitude have commonly been used for space weather operations. Yet, their temporal cadence is low and their intensity scale is crude. To derive a new generation of geomagnetic indices, it is desirable to establish a geomagnetic baseline that defines the quiet‐level of activity without solar‐driven perturbations. We present a new approach for deriving a baseline that represents the time‐dependent quiet variations focusing on data from Chambon‐la‐Forêt, France. Using a filtering technique, the measurements are first decomposed into the above‐diurnal (>24 hr) variation and the sum of 24, 12, 8, and 6 hr filters, called the daily variation. Using parameters that correlate with the ionospheric solar‐quiet (Sq) currents, we predict the daily “quiet” variation that excludes the effects of solar‐transient perturbations. Here, we train long short‐term memory neural networks using at least 11 years of data at 1 hr cadence. This predicted daily quiet variation is combined with linear extrapolation of the secular trend associated with the intrinsic geomagnetic variability, which dominates the above‐diurnal variation, to yield a local geomagnetic baseline. Unlike the existing baselines, our baseline is insensitive to geomagnetic storms. It is thus suitable for future definitions of geomagnetic indices that accurately reflect the intensity of solar‐driven perturbations. Our methodology is quick to implement and scalable, making it suitable for real‐time operation. Strategies for operational forecasting of our geomagnetic baseline 1 day and 27 days in advance are presented.https://doi.org/10.1029/2024SW004192geomagnetic baselinegeomagnetic indexspace weatherneural networksionospheregeomagnetism
spellingShingle Rungployphan Kieokaew
Veronika Haberle
Aurélie Marchaudon
Pierre‐Louis Blelly
Aude Chambodut
A Novel Neural Network‐Based Approach to Derive a Local Geomagnetic Baseline for Future Robust Characterization of Geomagnetic Indices at Mid‐Latitude
Space Weather
geomagnetic baseline
geomagnetic index
space weather
neural networks
ionosphere
geomagnetism
title A Novel Neural Network‐Based Approach to Derive a Local Geomagnetic Baseline for Future Robust Characterization of Geomagnetic Indices at Mid‐Latitude
title_full A Novel Neural Network‐Based Approach to Derive a Local Geomagnetic Baseline for Future Robust Characterization of Geomagnetic Indices at Mid‐Latitude
title_fullStr A Novel Neural Network‐Based Approach to Derive a Local Geomagnetic Baseline for Future Robust Characterization of Geomagnetic Indices at Mid‐Latitude
title_full_unstemmed A Novel Neural Network‐Based Approach to Derive a Local Geomagnetic Baseline for Future Robust Characterization of Geomagnetic Indices at Mid‐Latitude
title_short A Novel Neural Network‐Based Approach to Derive a Local Geomagnetic Baseline for Future Robust Characterization of Geomagnetic Indices at Mid‐Latitude
title_sort novel neural network based approach to derive a local geomagnetic baseline for future robust characterization of geomagnetic indices at mid latitude
topic geomagnetic baseline
geomagnetic index
space weather
neural networks
ionosphere
geomagnetism
url https://doi.org/10.1029/2024SW004192
work_keys_str_mv AT rungployphankieokaew anovelneuralnetworkbasedapproachtoderivealocalgeomagneticbaselineforfuturerobustcharacterizationofgeomagneticindicesatmidlatitude
AT veronikahaberle anovelneuralnetworkbasedapproachtoderivealocalgeomagneticbaselineforfuturerobustcharacterizationofgeomagneticindicesatmidlatitude
AT aureliemarchaudon anovelneuralnetworkbasedapproachtoderivealocalgeomagneticbaselineforfuturerobustcharacterizationofgeomagneticindicesatmidlatitude
AT pierrelouisblelly anovelneuralnetworkbasedapproachtoderivealocalgeomagneticbaselineforfuturerobustcharacterizationofgeomagneticindicesatmidlatitude
AT audechambodut anovelneuralnetworkbasedapproachtoderivealocalgeomagneticbaselineforfuturerobustcharacterizationofgeomagneticindicesatmidlatitude
AT rungployphankieokaew novelneuralnetworkbasedapproachtoderivealocalgeomagneticbaselineforfuturerobustcharacterizationofgeomagneticindicesatmidlatitude
AT veronikahaberle novelneuralnetworkbasedapproachtoderivealocalgeomagneticbaselineforfuturerobustcharacterizationofgeomagneticindicesatmidlatitude
AT aureliemarchaudon novelneuralnetworkbasedapproachtoderivealocalgeomagneticbaselineforfuturerobustcharacterizationofgeomagneticindicesatmidlatitude
AT pierrelouisblelly novelneuralnetworkbasedapproachtoderivealocalgeomagneticbaselineforfuturerobustcharacterizationofgeomagneticindicesatmidlatitude
AT audechambodut novelneuralnetworkbasedapproachtoderivealocalgeomagneticbaselineforfuturerobustcharacterizationofgeomagneticindicesatmidlatitude