# Two-Stage Microseismic P-Wave Arrival Picking via STA/LTA-Guided Lightweight U-Net

## TL;DR

This paper introduces a two-stage method for detecting P-wave arrivals in microseismic data, combining fast STA/LTA detection with a lightweight U-Net for improved accuracy and efficiency.

## Contribution

A novel two-stage framework that integrates STA/LTA with a lightweight U-Net for efficient and accurate microseismic P-wave picking.

## Key findings

- The method achieves a hit rate of 63.21% within ±0.01 s tolerance on 500 Hz microseismic data.
- It outperforms CNN and STA/LTA methods by 25.42% and 40.47%, respectively, with a mean absolute error of 0.0130 s.
- The model shows strong generalization and noise robustness on independent test sets.

## Abstract

Accurate picking of microseismic P-wave arrival times is essential for the localization and monitoring of mining-induced seismic events. Conventional Short-Term Average/Long-Term Average (STA/LTA) detectors, while computationally efficient, are highly susceptible to noise interference. Conversely, deep learning approaches exhibit superior noise robustness but often involve substantial computational redundancy and compromised real-time performance. To address these limitations, we propose a novel two-stage picking framework that integrates STA/LTA with a lightweight U-Net, enabling rapid preliminary detection followed by fine-grained refinement. In the first stage, STA/LTA rapidly scans continuous waveforms to identify candidate windows potentially containing P-wave arrivals. In the second stage, a lightweight U-Net performs sample-level regression within each candidate window to refine arrival-time estimates with high precision. This coarse-to-fine paradigm effectively balances computational efficiency and picking accuracy. Experimental validation on 500 Hz microseismic data acquired from a coal mine in Gansu Province demonstrates that the proposed method achieves a hit rate of 63.21% within a tolerance window of ±0.01 s. This represents performance improvements of 25.42% and 40.47% over convolutional neural network (CNN) and STA/LTA methods, respectively, while reducing the mean absolute error to 0.0130 s. Furthermore, the model exhibits consistent performance on independent test sets, confirming its generalization capability and noise robustness. By combining the computational efficiency of STA/LTA with the representational power of deep learning, the proposed approach demonstrates significant potential for real-time industrial deployment.