Improving Real-Time Forecasts of Induced Seismicity Through Machine Learning-Based Event Classification with an Attention-Enhanced U-Net Architecture

Avigyan Chatterjee, Qingkai Kong, Kayla Kroll, Chengping Chai, Paul Friberg, Alex Dzubay, Jeffrey Liefer, Scott Fertig, & Josh Stachnik

Submitted September 7, 2025, SCEC Contribution #14589, 2025 SCEC Annual Meeting Poster #TBD

Accurate and rapid classification of seismic events is essential for real-time monitoring and informed decision-making in subsurface industrial operations. In this project, we advance seismic event classification by developing a robust machine learning (ML) pipeline designed to distinguish events of interest (such as local earthquakes) from extraneous signals, including anthropogenic noise, weather-related disturbances, and teleseismic events, in real time. Utilizing a labeled dataset of over 100,000 seismic events and false positive detections, we assess several deep learning architectures, including Convolutional Neural Networks (CNN), U-Net, and U-Net models enhanced with self-attention mechanisms. After initial binary classification at the single-station level, predictions from all stations are combined to produce a final event classification across the network. Our experimental results show that the top-performing model achieves a classification accuracy of 95% and an area under the Receiver Operating Characteristic curve (AUC) of 0.95, substantially reducing false positives compared to traditional methods. Integrating this ML-based classification module into the real-time seismic processing workflow is expected to minimize manual review by filtering out likely false detections. Ultimately, this approach enables the delivery of high-fidelity, real-time seismic catalogs to industrial operators and the DOE’s ORION toolkit, supporting improved operational forecasting and hazard assessment.

This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344 bearing release number LLNL-ABS-200996.This project is supported by funding from the U.S. Department of Energy’s Office of Fossil Energy and Carbon Management via the Technology Commercialization Fund (TCF) bearing award number L110-1608, which is administered by the Office of Technology Commercialization. The TCF aims to promote the commercialization of DOE National Lab, plant, and site technologies and build out the National Lab commercialization ecosystem.

Key Words
Machine Learning, Induced Seismicity, Earthquake Detection

Citation
Chatterjee, A., Kong, Q., Kroll, K., Chai , C., Friberg, P., Dzubay, A., Liefer, J., Fertig, S., & Stachnik, J. (2025, 09). Improving Real-Time Forecasts of Induced Seismicity Through Machine Learning-Based Event Classification with an Attention-Enhanced U-Net Architecture. Poster Presentation at 2025 SCEC Annual Meeting.

Related Projects & Working Groups
Earthquake Forecasting and Predictability (EFP)