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...

3-D acquisition geometry analysis: Incorporating information from multiples

Recent advances in survey design have led to conventional common-midpoint-based analysis being replaced by the subsurface-based seismic acquisition analysis and design, with the emphasis on advance techniques of illumination analysis. Amongst them are wave-equation-based seismic illumination analyses such as the so-called focal beam method. The...

3D primary estimation by sparse inversion using the focal domain parameterization

Recently, a new approach to multiple removal has been intro- duced: estimation of primaries by sparse inversion (EPSI). Al- though based on the same relationship between primaries and multiples as surface-related multiple elimination (SRME), it involves quite a different process: instead of prediction and subtraction of multiples, in EPSI the...