Centre de documentation
scientifique

Volcano-seismic transfer learning and uncertainty quantification with bayesian neural networks / Angel Bueno in IEEE Transactions on geoscience and remote sensing, vol 58 n° 2 (February 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 2 (February 2020) . - pp Titre : Volcano-seismic transfer learning and uncertainty quantification with bayesian neural networks Type de document : Article/Communication Auteurs : Angel Bueno, Auteur ; Carmen Benitez, Auteur ; Silvio De Angelis, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes IGN] apprentissage profond [Termes IGN] classification bayesienne [Termes IGN] classification par réseau neuronal [Termes IGN] forme d'onde [Termes IGN] incertitude des données [Termes IGN] réseau bayesien [Termes IGN] réseau neuronal profond [Termes IGN] Russie [Termes IGN] séisme [Termes IGN] sismologie [Termes IGN] surveillance géologique [Termes IGN] volcanologie [Termes IGN] Washington (Etats-Unis ; état) Résumé : (auteur) Over the past few years, deep learning (DL) has emerged as an important tool in the fields of volcano and earthquake seismology. However, these methods have been applied without performing thorough analyses of the associated uncertainties. Here, we propose a solution to enhance volcano-seismic monitoring systems, through probabilistic Bayesian DL; we implement and demonstrate a workflow for waveform classification, rapid quantification of the associated uncertainty, and link these uncertainties to changes in volcanic unrest. Specifically, we introduce Bayesian neural networks (BNNs) to perform event identification, classification, and their estimated uncertainty on data gathered at two active volcanoes, Mount St. Helens, Washington, USA, and Bezymianny, Kamchatka, Russia. We demonstrate how BNNs achieve excellent performance (92.08%) in discriminating both the type of event and its origin when the two data sets are merged together, and no additional training information is provided. Finally, we demonstrate that the data representations learned by the BNNs are transferable across different eruptive periods. We also find that the estimated uncertainty is related to changes in the state of unrest at the volcanoes and propose that it could be used to gauge whether the learned models may be exported to other eruptive scenarios. Numéro de notice : A2020-094 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2941494 Date de publication en ligne : 07/10/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2941494 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94657 [article]