Perol Thibaut, Gharbi Michaël, Denolle Marine
John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA.
Gram Labs Inc., Arlington, VA 22201, USA.
Sci Adv. 2018 Feb 14;4(2):e1700578. doi: 10.1126/sciadv.1700578. eCollection 2018 Feb.
The recent evolution of induced seismicity in Central United States calls for exhaustive catalogs to improve seismic hazard assessment. Over the last decades, the volume of seismic data has increased exponentially, creating a need for efficient algorithms to reliably detect and locate earthquakes. Today's most elaborate methods scan through the plethora of continuous seismic records, searching for repeating seismic signals. We leverage the recent advances in artificial intelligence and present ConvNetQuake, a highly scalable convolutional neural network for earthquake detection and location from a single waveform. We apply our technique to study the induced seismicity in Oklahoma, USA. We detect more than 17 times more earthquakes than previously cataloged by the Oklahoma Geological Survey. Our algorithm is orders of magnitude faster than established methods.
美国中部近期诱发地震活动的演变需要详尽的目录来改进地震危险性评估。在过去几十年中，地震数据量呈指数级增长，这就需要高效算法来可靠地检测和定位地震。如今最精细的方法是扫描大量连续地震记录，寻找重复的地震信号。我们利用人工智能的最新进展，提出了ConvNetQuake，这是一种用于从单个波形检测和定位地震的高度可扩展卷积神经网络。我们将我们的技术应用于研究美国俄克拉荷马州的诱发地震活动。我们检测到的地震数量比俄克拉荷马地质调查局之前编录的多17倍以上。我们的算法比现有方法快几个数量级。
