Identifying Asperity Patterns Via Machine Learning Algorithms

Abstract : An asperity’s location is very crucial in the spatiotemporal analysis of an area’s seismicity. In literature, b-value and seismic density have been proven as useful indicators for asperity location. In this paper, machine learning techniques are used to locate areas with high probability of asperity existence using as feature vector information extracted solely by earthquake catalogs. Many machine learning algorithms are tested to identify those with the best results. This method is tested for data from the wider region of Hokkaido, Japan where in an earlier study asperities have been detected.
Type de document :
Communication dans un congrès
Lazaros Iliadis; Ilias Maglogiannis. 12th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2016, Thessaloniki, Greece. IFIP Advances in Information and Communication Technology, AICT-475, pp.87-93, 2016, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-319-44944-9_8〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01557625
Contributeur : Hal Ifip <>
Soumis le : jeudi 6 juillet 2017 - 13:55:24
Dernière modification le : vendredi 1 décembre 2017 - 01:16:26
Document(s) archivé(s) le : mercredi 24 janvier 2018 - 02:58:38

Fichier

 Accès restreint
Fichier visible le : 2019-01-01

Connectez-vous pour demander l'accès au fichier

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Kostantinos Arvanitakis, Markos Avlonitis. Identifying Asperity Patterns Via Machine Learning Algorithms. Lazaros Iliadis; Ilias Maglogiannis. 12th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2016, Thessaloniki, Greece. IFIP Advances in Information and Communication Technology, AICT-475, pp.87-93, 2016, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-319-44944-9_8〉. 〈hal-01557625〉

Partager

Métriques

Consultations de la notice

27