Microseismic event classification with time, frequency and wavelet domain convolutional neural networks
Jiang, Jiaxin and Stankovic, Vladimir and Stankovic, Lina and Parastatidis, Emmanouil and Pytharouli, Stella (2023) Microseismic event classification with time, frequency and wavelet domain convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing. ISSN 0196-2892 (https://doi.org/10.1109/TGRS.2023.3262412)
Preview |
Text.
Filename: Jiang_etal_IEEETGRS_2023_Microseismic_event_classification_with_time_frequency_and_wavelet_domain.pdf
Accepted Author Manuscript License: ![]() Download (9MB)| Preview |
Abstract
Passive seismics help us understand subsurface processes, e.g. landslides, mining, geothermal systems etc. and help predict and mitigate their effects. Continuous monitoring results in long seismic records that may contain various sources, which need to be classified. Manual detection and labeling of recorded seismic events is not only time consuming but can also be inconsistent when done manually, even in the case where it is done by the same expert. Therefore, an automated approach for classification of continuous microseismic recordings based on a Convolutional Neural Network (CNN) is proposed, with a multiclassifier architecture that classifies earthquakes, rockfalls and low signal to noise ratio quakes. Furthermore, we propose three CNN architectures that take as input time series data, Short Time Fourier Transform (STFT) and Continuous Wavelet Transform (CWT) maps. The suitability of these three networks is rigorously assessed over five months of continuous seismometer recordings from the active Super-Sauze landslide in France. We observe that all three architectures have excellent and very similar performance. Furthermore, we evaluate transferability to a geographically distinct seismically active site in Larissa, Greece. We demonstrate that the proposed network is able to detect all 86 catalogued earthquake events, having only been trained on the Super-Sauze dataset and shows good agreement with manually detected events. This is promising as it could replace painstaking manual labelling of events in large recordings.
ORCID iDs
Jiang, Jiaxin, Stankovic, Vladimir



Persistent Identifier
https://doi.org/10.17868/strath.00084907-
-
Item type: Article ID code: 84907 Dates: DateEvent27 March 2023Published27 March 2023Published Online17 March 2023Accepted30 March 2022SubmittedKeywords: microseismic event classification, continuous wavelet transform, short time Fourier transform, Electrical Engineering. Electronics Nuclear Engineering, Environmental engineering, Electrical and Electronic Engineering, Earth and Planetary Sciences(all), Environmental Engineering, SDG 9 - Industry, Innovation, and Infrastructure, SDG 11 - Sustainable Cities and Communities, SDG 13 - Climate Action Subjects: Technology > Electrical engineering. Electronics Nuclear engineering
Technology > Engineering (General). Civil engineering (General) > Environmental engineeringDepartment: Faculty of Engineering > Electronic and Electrical Engineering
Faculty of Engineering > Civil and Environmental EngineeringDepositing user: Pure Administrator Date deposited: 28 Mar 2023 10:30 Last modified: 02 Jun 2023 00:42 URI: https://strathprints.strath.ac.uk/id/eprint/84907