Abstract: A machine learning system efficiently detects faults from three-dimensional (“3D”) seismic images, in which the fault detection is considered as a binary segmentation problem. Because the distribution of fault and nonfault samples is heavily biased, embodiments of the present disclosure use a balanced loss function to optimize model parameters. Embodiments of the present disclosure train a machine learning system by using a selected number of pairs of 3D synthetic seismic and fault volumes, which may be automatically generated by randomly adding folding, faulting, and noise in the volumes. Although trained by using only synthetic data sets, the machine learning system can accurately detect faults from 3D field seismic volumes that are acquired at totally different surveys.

Abstract: A machine learning system efficiently detects faults from three-dimensional (“3D”) seismic images, in which the fault detection is considered as a binary segmentation problem. Because the distribution of fault and nonfault samples is heavily biased, embodiments of the present disclosure use a balanced loss function to optimize model parameters. Embodiments of the present disclosure train a machine learning system by using a selected number of pairs of 3D synthetic seismic and fault volumes, which may be automatically generated by randomly adding folding, faulting, and noise in the volumes. Although trained by using only synthetic data sets, the machine learning system can accurately detect faults from 3D field seismic volumes that are acquired at totally different surveys.

Abstract: The present disclosure provides a system and method for estimating fracture density within a subsurface formation from S-wave seismic data. In one embodiment, the S-wave seismic data is separated into fast (“S1”) and slow (“S2”) data. A computer is used to compute local similarity of the S1 and S2 data and to compute a cumulative time-difference by which the S2 data lags the S1 data from the local similarity. Based on the computed cumulative time-difference, the fracture density of a subsurface formation is estimated.

Abstract: In some embodiments, input seismic data is decomposed into Gaussian beams using plane wave destructor (PWD) filters. The beams are used in a fast beam migration method to generate a seismic image of a subsurface volume of interest. PWD filters are applied to groups of neighboring traces to generate a field of dips/curvatures that fit the input trace data. Beam wavelets are then formed according to the dip/curvature field. Multiple dips (PWD slopes) may be determined at each location in time/space in order to handle intersecting reflection events. Exemplary methods allow an improvement in processing speed by more than an order of magnitude as compared to standard industry techniques such as Kirchhoff migration.

Abstract: The present disclosure provides a system and method for estimating fracture density within a subsurface formation from S-wave seismic data. In one embodiment, the S-wave seismic data is separated into fast (“S1”) and slow (“S2”) data. A computer is used to compute local similarity of the S1 and S2 data and to compute a cumulative time-difference by which the S2 data lags the S1 data from the local similarity. Based on the computed cumulative time-difference, the fracture density of a subsurface formation is estimated.