INSTANCE – the Italian seismic dataset for machine learning
INSTANCE — итальянский сейсмический набор данных для машинного обучения
2021-11-30
SCID: 54.1/f3n4af9q
Discuss with AI
HDF5 formatItalian National Seismic NetworkItalian seismic datasetearthquake waveformsmachine learning
Figures from the paper
Abstract (AI)
The Italian earthquake waveform data are collected here in a dataset suited for machine learning analysis (ML) applications. The dataset consists of nearly 1.2 million three-component (3C) waveform traces from about 50 000 earthquakes and more than 130 000 noise 3C waveform traces, for a total of about 43 000 h of data and an average of 21 3C traces provided per event. The earthquake list is based on the Italian Seismic Bulletin (http://terremoti.ingv.it/bsi, last access: 15 February 2020) of the Istituto Nazionale di Geofisica e Vulcanologia between January 2005 and January 2020, and it includes events in the magnitude range between 0.0 and 6.5. The waveform data have been recorded primarily by the Italian National Seismic Network (network code IV) and include both weak- (HH, EH channels) and strong-motion (HN channels) recordings. All the waveform traces have a length of 120 s, are sampled at 100 Hz, and are provided both in counts and ground motion physical units after deconvolution of the instrument transfer functions. The waveform dataset is accompanied by metadata consisting of more than 100 parameters providing comprehensive information on the earthquake source, the recording stations, the trace features, and other derived quantities. This rich set of metadata allows the users to target the data selection for their own purposes. Much of these metadata can be used as labels in ML analysis or for other studies. The dataset, assembled in HDF5 format, is available at http://doi.org/10.13127/instance (Michelini et al., 2021).
Key Findings
1
Each waveform is 120 seconds long, sampled at 100 Hz, and supplied both in raw counts and deconvolved ground-motion units.
2
INSTANCE provides approximately 1.2 million three-component earthquake waveforms from about 50,000 Italian earthquakes, plus over 130,000 noise traces.
3
More than 100 metadata parameters describe earthquake sources, stations, waveform features, and derived quantities, enabling targeted data selection and machine-learning labels.
4
The dataset contains approximately 43,000 hours of data and is distributed in HDF5 format for machine-learning and other seismic studies.
5
The dataset covers earthquakes from magnitude 0.0 to 6.5 recorded between January 2005 and January 2020, primarily by the Italian National Seismic Network.
Research Object
The INSTANCE Italian earthquake waveform dataset, comprising three-component earthquake and noise recordings from Italy (2005–2020)
Research Subject
The dataset’s suitability and metadata-supported structure for machine-learning analysis and targeted selection of earthquake waveform data
Publication Details
Publication Date
2021-11-30
Journal
Publisher
ISSN
Cited by
172
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai6
SciPy 1.0: fundamental algorithms for scientific computing in Python2020
PyTorch: An Imperative Style, High-Performance Deep Learning Library2019
Array programming with NumPy2020
Data Structures for Statistical Computing in Python2010
Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking2020
Reliable Real‐Time Seismic Signal/Noise Discrimination With Machine Learning2018