Gaviano, S. (2022) Machine learning analysis of a local seismic network in Mt. Amiata (Italy). Il nuovo cimento C, 45 (4). pp. 1-10. ISSN 1826-9885
Text
ncc12438.pdf - Published Version Download (819kB) |
Abstract
Since March 2016 a small network of 11 seismic stations, deployed by Istituto Nazionale di Geofisica e Vulcanologia (INGV), has recorded about 1000 earthquakes in the southern part of Mt. Amiata. The continuous seismic waveforms are reprocessed with phase recognition pickers based on machine learning (ML) algorithms trained with global datasets of local earthquakes to get a more comprehensive earthquake catalog. This new catalog is compared with the already available events picked and located manually to assess the performance of ML-based analysis. The manually detected earthquakes are then used to assemble a dataset suitable for ML analysis. In a later stage, we investigate how the automatic detection performance could be further enhanced with specific training of the ML pickers with data coming from the INGV network (INSTANCE dataset) and from the local network itself.
Item Type: | Article |
---|---|
Subjects: | 500 Scienze naturali e Matematica > 530 Fisica |
Depositing User: | Marina Spanti |
Date Deposited: | 06 Sep 2022 11:37 |
Last Modified: | 06 Sep 2022 11:37 |
URI: | http://eprints.bice.rm.cnr.it/id/eprint/21991 |
Actions (login required)
View Item |