Pre-Earthquake Ionospheric Perturbation Identification Using CSES Data via Transfer Learning

During the lithospheric buildup to an earthquake, complex physical changes occur within the earthquake hypocenter. Data pertaining to the changes in the ionosphere may be obtained by satellites, and the analysis of data anomalies can help identify earthquake precursors. In this paper, we present a d...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pan Xiong, Cheng Long, Huiyu Zhou, Roberto Battiston, Angelo De Santis, Dimitar Ouzounov, Xuemin Zhang, Xuhui Shen
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	earthquake pre-earthquake anomalies CSES and DEMETER satellites ionospheric plasma transfer deep learning physical mechanisms Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/58fe2d9e1539444a85cb091e28c8700e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:58fe2d9e1539444a85cb091e28c8700e
record_format	dspace
spelling	oai:doaj.org-article:58fe2d9e1539444a85cb091e28c8700e2021-11-05T16:52:42ZPre-Earthquake Ionospheric Perturbation Identification Using CSES Data via Transfer Learning2296-665X10.3389/fenvs.2021.779255https://doaj.org/article/58fe2d9e1539444a85cb091e28c8700e2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fenvs.2021.779255/fullhttps://doaj.org/toc/2296-665XDuring the lithospheric buildup to an earthquake, complex physical changes occur within the earthquake hypocenter. Data pertaining to the changes in the ionosphere may be obtained by satellites, and the analysis of data anomalies can help identify earthquake precursors. In this paper, we present a deep-learning model, SeqNetQuake, that uses data from the first China Seismo-Electromagnetic Satellite (CSES) to identify ionospheric perturbations prior to earthquakes. SeqNetQuake achieves the best performance [F-measure (F1) = 0.6792 and Matthews correlation coefficient (MCC) = 0.427] when directly trained on the CSES dataset with a spatial window centered on the earthquake epicenter with the Dobrovolsky radius and an input sequence length of 20 consecutive observations during night time. We further explore a transferring learning approach, which initially trains the model with the larger Electro-Magnetic Emissions Transmitted from the Earthquake Regions (DEMETER) dataset, and then tunes the model with the CSES dataset. The transfer-learning performance is substantially higher than that of direct learning, yielding a 12% improvement in the F1 score and a 29% improvement in the MCC value. Moreover, we compare the proposed model SeqNetQuake with other five benchmarking classifiers on an independent test set, which shows that SeqNetQuake demonstrates a 64.2% improvement in MCC and approximately a 24.5% improvement in the F1 score over the second-best convolutional neural network model. SeqNetSquake achieves significant improvement in identifying pre-earthquake ionospheric perturbation and improves the performance of earthquake prediction using the CSES data.Pan XiongCheng LongHuiyu ZhouRoberto BattistonRoberto BattistonAngelo De SantisDimitar OuzounovXuemin ZhangXuhui ShenFrontiers Media S.A.articleearthquakepre-earthquake anomaliesCSES and DEMETER satellitesionospheric plasmatransfer deep learningphysical mechanismsEnvironmental sciencesGE1-350ENFrontiers in Environmental Science, Vol 9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	earthquake pre-earthquake anomalies CSES and DEMETER satellites ionospheric plasma transfer deep learning physical mechanisms Environmental sciences GE1-350
spellingShingle	earthquake pre-earthquake anomalies CSES and DEMETER satellites ionospheric plasma transfer deep learning physical mechanisms Environmental sciences GE1-350 Pan Xiong Cheng Long Huiyu Zhou Roberto Battiston Roberto Battiston Angelo De Santis Dimitar Ouzounov Xuemin Zhang Xuhui Shen Pre-Earthquake Ionospheric Perturbation Identification Using CSES Data via Transfer Learning
description	During the lithospheric buildup to an earthquake, complex physical changes occur within the earthquake hypocenter. Data pertaining to the changes in the ionosphere may be obtained by satellites, and the analysis of data anomalies can help identify earthquake precursors. In this paper, we present a deep-learning model, SeqNetQuake, that uses data from the first China Seismo-Electromagnetic Satellite (CSES) to identify ionospheric perturbations prior to earthquakes. SeqNetQuake achieves the best performance [F-measure (F1) = 0.6792 and Matthews correlation coefficient (MCC) = 0.427] when directly trained on the CSES dataset with a spatial window centered on the earthquake epicenter with the Dobrovolsky radius and an input sequence length of 20 consecutive observations during night time. We further explore a transferring learning approach, which initially trains the model with the larger Electro-Magnetic Emissions Transmitted from the Earthquake Regions (DEMETER) dataset, and then tunes the model with the CSES dataset. The transfer-learning performance is substantially higher than that of direct learning, yielding a 12% improvement in the F1 score and a 29% improvement in the MCC value. Moreover, we compare the proposed model SeqNetQuake with other five benchmarking classifiers on an independent test set, which shows that SeqNetQuake demonstrates a 64.2% improvement in MCC and approximately a 24.5% improvement in the F1 score over the second-best convolutional neural network model. SeqNetSquake achieves significant improvement in identifying pre-earthquake ionospheric perturbation and improves the performance of earthquake prediction using the CSES data.
format	article
author	Pan Xiong Cheng Long Huiyu Zhou Roberto Battiston Roberto Battiston Angelo De Santis Dimitar Ouzounov Xuemin Zhang Xuhui Shen
author_facet	Pan Xiong Cheng Long Huiyu Zhou Roberto Battiston Roberto Battiston Angelo De Santis Dimitar Ouzounov Xuemin Zhang Xuhui Shen
author_sort	Pan Xiong
title	Pre-Earthquake Ionospheric Perturbation Identification Using CSES Data via Transfer Learning
title_short	Pre-Earthquake Ionospheric Perturbation Identification Using CSES Data via Transfer Learning
title_full	Pre-Earthquake Ionospheric Perturbation Identification Using CSES Data via Transfer Learning
title_fullStr	Pre-Earthquake Ionospheric Perturbation Identification Using CSES Data via Transfer Learning
title_full_unstemmed	Pre-Earthquake Ionospheric Perturbation Identification Using CSES Data via Transfer Learning
title_sort	pre-earthquake ionospheric perturbation identification using cses data via transfer learning
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/58fe2d9e1539444a85cb091e28c8700e
work_keys_str_mv	AT panxiong preearthquakeionosphericperturbationidentificationusingcsesdataviatransferlearning AT chenglong preearthquakeionosphericperturbationidentificationusingcsesdataviatransferlearning AT huiyuzhou preearthquakeionosphericperturbationidentificationusingcsesdataviatransferlearning AT robertobattiston preearthquakeionosphericperturbationidentificationusingcsesdataviatransferlearning AT robertobattiston preearthquakeionosphericperturbationidentificationusingcsesdataviatransferlearning AT angelodesantis preearthquakeionosphericperturbationidentificationusingcsesdataviatransferlearning AT dimitarouzounov preearthquakeionosphericperturbationidentificationusingcsesdataviatransferlearning AT xueminzhang preearthquakeionosphericperturbationidentificationusingcsesdataviatransferlearning AT xuhuishen preearthquakeionosphericperturbationidentificationusingcsesdataviatransferlearning
_version_	1718444102319603712

Pre-Earthquake Ionospheric Perturbation Identification Using CSES Data via Transfer Learning

Ejemplares similares