Microseismic event classification with a lightweight Fourier Neural Operator model

2025-12-08

AI Summary

To address the challenges of low classification accuracy, high computational overhead, and poor deployability on continuous seismic data streams in real-time induced-seismicity monitoring, this paper proposes a lightweight Fourier Neural Operator (FNO) model. It is the first to adapt FNO for microseismic waveform classification, leveraging its inherent frequency-domain modeling capability, global receptive field, and parameter efficiency to achieve strong generalization even under extremely sparse training sample densities. A resolution-invariant architecture is introduced to substantially reduce computational resource requirements. Evaluated on the STEAD dataset and real-world microseismic data, the model achieves F1 scores of 95% and 98%, respectively—surpassing state-of-the-art deep learning methods. It thus achieves an effective trade-off among high accuracy (>95%), low power consumption, and real-time inference capability, enabling direct deployment in field applications such as traffic-light-based online decision systems.

Technology Category

• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Real-time monitoring of induced seismicity is crucial for mitigating operational hazards, relying on the rapid and accurate classification of microseismic events from continuous data streams. However, while many deep learning models excel at this task, their high computational requirements often limit their practical application in real-time monitoring systems. To address this limitation, a lightweight model based on the Fourier Neural Operator (FNO) is proposed for microseismic event classification, leveraging its inherent resolution-invariance and computational efficiency for waveform processing. In the STanford EArthquake Dataset (STEAD), a global and large-scale database of seismic waveforms, the FNO-based model demonstrates high effectiveness for trigger classification, with an F1 score of 95% even in the scenario of data sparsity in training. The new FNO model greatly decreases the computer power needed relative to current deep learning models without sacrificing the classification success rate measured by the F1 score. A test on a real microseismic dataset shows a classification success rate with an F1 score of 98%, outperforming many traditional deep-learning techniques. A combination of high success rate and low computational power indicates that the FNO model can serve as a methodology of choice for real-time monitoring of microseismicity for induced seismicity. The method saves computational resources and facilitates both post-processing and real-time seismic processing suitable for the implementation of traffic light systems to prevent undesired induced seismicity.

Problem

• Classify microseismic events in real-time monitoring
• Reduce computational demands of deep learning models
• Maintain high accuracy with lightweight Fourier Neural Operator

Innovation

• Lightweight Fourier Neural Operator for microseismic classification
• Achieves high F1 scores with reduced computational power
• Enables real-time monitoring with resolution-invariant waveform processing