MicroPhaseNO: Adapting an Earthquake-Trained Phase Neural Operator for Microseismic Phase Picking

2025-12-15

AI Summary

Microseismic phase picking faces challenges including low signal-to-noise ratio, short event duration, and inconsistent annotation conventions (peak/trough rather than first-arrival). Existing deep learning models pretrained on large-earthquake data exhibit limited generalizability to microseismic scenarios. This paper proposes Phase Neural Operator (PhaseNO) transfer adaptation tailored for microseismic applications: it is the first work to adapt a seismology-pretrained PhaseNO model to microseismic phase picking, requiring only 200 labeled samples for few-shot fine-tuning; it supports dual-mode (peak and trough) picking, effectively mitigating systematic temporal bias and uncertainty. Evaluated on three real-world microseismic datasets, our method achieves up to a 30% improvement in F1-score and accuracy, with significantly reduced temporal picking bias. The implementation code is publicly available.

Technology Category

• Natural Language Processing: Learning & Optimization for NLP
• Search and Optimization: Learning to Search
• Machine Learning: Semi-Supervised Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Seismic phase picking is very often used for microseismic monitoring and subsurface imaging. Traditional manual processing is not feasible for either real-time applications or large arrays. Deep learning-based pickers trained on large earthquake catalogs offer an automated alternative. However, they are typically optimized for high signal-to-noise, long-duration networks and struggle with the challenges presented by microseismic datasets, which are purpose-built for limited time without previously detected seismicity. In this study, we demonstrate how a network-wide earthquake phase picker, the Phase Neural Operator (PhaseNO), can be adapted to microseismic monitoring using transfer learning. Starting from a PhaseNO model pre-trained on more than 57,000 three-component earthquake and noise records, we fine-tune the model using only 200 labeled and noise seismograms from induced events in hydraulic-fracturing settings. The fine-tuned model thus preserves the rich spatio-temporal representation learned from abundant earthquake data, while adapting to the characteristics and labeling conventions of microseismic phases, which are often picked on peaks or troughs rather than onsets. We evaluate performance on three distinct real-world microseismic datasets with different network geometries and acquisition parameters. Compared to the original PhaseNO and a conventional workflow, the adapted model increases F1 score and accuracy by up to 30%, and strongly reduces systematic timing bias and pick uncertainty. Because the adaptation relies on a small, campaign-specific calibration set, the approach is readily transferable to other microseismic tasks where public earthquake data and pre-trained models are accessible. The associated code will be released openly at https://github.com/ayratabd/MicroPhaseNO.

Problem

• Adapts earthquake-trained neural operator for microseismic phase picking
• Addresses challenges of low signal-to-noise and limited data in microseismic monitoring
• Improves accuracy and reduces timing bias via small dataset fine-tuning

Innovation

• Transfer learning adapts earthquake-trained neural operator
• Fine-tuning with 200 microseismic records enhances phase picking
• Model reduces timing bias and increases accuracy by 30%