← Back to Gallery

A Neural Network Based Small Seismic Event Detector and Locator

Small seismic events are abundant and can provide a lot of information on the subsurface. The ability to automatically detect small seismic events in an accurate and efficient way is of great interest for the study of geological structure and fault process. Small seismic events are difficult to detect using conventional methods as the amplitudes of signals are relatively small. Here we present two efficient models: a detector that could accurately extract small seismic signals from continuous records and a locator that determines the geographical position of the extracted event. Both of our models are based on a convolution neural network with a skip-connected structure. Features are learned from spectrograms of signals and then used to classify windows of seismic records. We demonstrate the performance of our algorithms using dataset from Oklahoma, where seismicity has increased dramatically over the last decade. We show that our algorithms are efficient at detecting and locating small seismic events, resulting in a much more comprehensive catalog compared with the Oklahoma Geological Survey (OGS) catalog.

Presenting Author: Xiaofei Ma

Additional Authors