Johnson Sean W, Chambers Derrick J A, Boltz Michael S, Koper Keith D
National Institute for Occupational Safety and Health, Spokane Mining Research Division, 315 E Montgomery Av., Spokane WA, 99207, USA.
University of Utah Seismograph Stations, 115 South 1460 East, Room 211 FASB SLC, UT 84112-0102, USA.
Geophys J Int. 2021 Jan 1;224(1):230-240.
Monitoring mining-induced seismicity (MIS) can help engineers understand the rock mass response to resource extraction. With a thorough understanding of ongoing geomechanical processes, engineers can operate mines, especially those mines with the propensity for rock-bursting, more safely and efficiently. Unfortunately, processing MIS data usually requires significant effort from human analysts, which can result in substantial costs and time commitments. The problem is exacerbated for operations that produce copious amounts of MIS, such as mines with high-stress and/or extraction ratios. Recently, deep learning methods have shown the ability to significantly improve the quality of automated arrival-time picking on earthquake data recorded by regional seismic networks. However, relatively little has been published on applying these techniques to MIS. In this study, we compare the performance of a convolutional neural network (CNN) originally trained to pick arrival times on the Southern California Seismic Network (SCSN) to that of human analysts on coal-mine-related MIS. We perform comparisons on several coal-related MIS data sets recorded at various network scales, sampling rates and mines. We find that the Southern-California-trained CNN does not perform well on any of our data sets without retraining. However, applying the concept of transfer learning, we retrain the SCSN model with relatively little MIS data after which the CNN performs nearly as well as a human analyst. When retrained with data from a single analyst, the analyst-CNN pick time residual variance is lower than the variance observed between human analysts. We also compare the retrained CNN to a simpler, optimized picking algorithm, which falls short of the CNN's performance. We conclude that CNNs can achieve a significant improvement in automated phase picking although some data set-specific training will usually be required. Moreover, initializing training with weights found from other, even very different, data sets can greatly reduce the amount of training data required to achieve a given performance threshold.
监测采矿诱发地震活动（MIS）有助于工程师了解岩体对资源开采的响应。通过深入了解正在进行的地质力学过程，工程师可以更安全、高效地运营矿山，尤其是那些有岩爆倾向的矿山。不幸的是，处理MIS数据通常需要人工分析师付出巨大努力，这可能导致高昂的成本和时间投入。对于产生大量MIS数据的作业，如高应力和/或开采率高的矿山，问题会更加严重。最近，深度学习方法已显示出能够显著提高区域地震台网记录的地震数据自动震相到时拾取的质量。然而，关于将这些技术应用于MIS的研究相对较少。在本研究中，我们将最初训练用于拾取南加州地震台网（SCSN）地震到时的卷积神经网络（CNN）的性能与人工分析师在煤矿相关MIS方面的性能进行了比较。我们对在不同网络规模、采样率和矿山记录的几个与煤相关的MIS数据集进行了比较。我们发现，未经重新训练，在南加州训练的CNN在我们的任何数据集上表现都不佳。然而，应用迁移学习的概念，我们用相对较少的MIS数据对SCSN模型进行重新训练，之后CNN的表现几乎与人工分析师一样好。当用来自单个分析师的数据进行重新训练时，分析师 - CNN拾取时间残差方差低于人工分析师之间观察到的方差。我们还将重新训练的CNN与一种更简单的优化拾取算法进行了比较，该算法的性能不及CNN。我们得出结论，尽管通常需要一些特定于数据集的训练，但CNN在自动震相拾取方面可以实现显著改进。此外，用从其他甚至非常不同的数据集找到的权重初始化训练，可以大大减少达到给定性能阈值所需的训练数据量。
