Applying EQTransformer to laboratory earthquakes: detecting and picking acoustic emissions with machine learning
Abstract Acoustic emissions (AEs) are bursts of elastic waves generated by ruptures in laboratory rock mechanics experiments that mirror typical seismograms recorded in natural earthquakes, albeit at much higher frequencies. Traditionally, AE events were manually sorted and picked—a time-consuming a...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-07-01
|
| Series: | Earth, Planets and Space |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40623-025-02237-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Acoustic emissions (AEs) are bursts of elastic waves generated by ruptures in laboratory rock mechanics experiments that mirror typical seismograms recorded in natural earthquakes, albeit at much higher frequencies. Traditionally, AE events were manually sorted and picked—a time-consuming and daunting task. Recently, automatic methods based on machine learning (ML) or template matching have been applied to detect AE events. In order to accurately and quickly analyze a large quantity of raw AE waveforms, the current study explores the direct application of ML tools designed for regular earthquake waveforms to the AE detection and picking process. We investigated applications of a deep-learning-based detector EQTransformer (EQT) that was trained on global earthquake data to laboratory AE datasets without retraining. Two AE datasets were collected from laboratory deformation experiments during the syn-deformational phase transformation from olivine to spinel in Mg2GeO4. We compared EQT’s performance on AEs to its published performance on natural earthquakes, as well as to a neural network (NN) designed for AE detection and picking called MultiNet. When applied to dataset D2540, EQT detected all 3901 previously identified events in the dataset with a mean P-pick error of < 1 sampling point, in addition to 2521 previously undetected events. For dataset D1247, EQT also detected all 550 known events with a mean error of < 1 sampling point, as well as 22 new events. In both cases, EQT performed within the standards advertised for EQT on earthquake data and with similar precision to MultiNet. Our results indicate that the EQT model pre-trained using global seismic data can be directly applied to accurately pick AE events in laboratory settings, with robust performance across multiple recording channels. Graphical Abstract |
|---|---|
| ISSN: | 1880-5981 |