Localizing weak microseismic events using transfer learning with a deep neural network

Retrieving accurate microseismic source locations induced by hydraulic-fracturing operations is an important step to gain insights into the hydraulically stimulated reservoir volume. Recently, deep neural networks have been proposed that directly recover source locations from the seismic waveforms. The optimal performance of the proposed deep...

Acoustic wavefield separation using horizontal receiver arrays deployed at multiple depths on land

We present a novel inversion scheme for decomposing upgoing and downgoing wavefields from vertical particle velocity recordings in downhole arrays at multiple depth levels. Our method requires no knowledge of the subsurface medium parameters as the required operators are obtained directly from the data by direct-wave interferometry. As we...