Innovative application of full-waveform inversion applied to extended wide-azimuth marine streamer seismic in a complex salt environment

We demonstrated the application of full-waveform inversion (FWI) guided velocity model building to an extended wide-azimuth towed streamer (EWATS) seismic data set in the Gulf of Mexico. Field data were collected over a historically challenging imaging area, colloquially called the “grunge zone” due to the formation of a compressional allosuture emplaced between two colliding salt sheets. These data had a poor subsalt image below the suture with conventional narrow-azimuth data. Additional geologic complexities were observed including high-velocity carbonate carapace near the top of salt and multiple intrasalt sedimentary inclusions. As such, improved seismic imaging was required to plan and execute wells targeting subsalt strata. Significant improvements to the velocity model and subsalt image were evident with wide-azimuth towed streamer and later EWATS data using conventional top-down velocity model building approaches. Then, high-impact improvements were made using EWATS data with an FWI velocity model building workflow; this study represented an early successful application of FWI used to update salt body geometries from streamer seismic data, in which many past applications were limited to improving sedimentary velocities. Later petrophysical data verified the new FWI-derived model, which had significantly increased confidence in the structural and stratigraphic interpretation of subsalt reservoir systems below the grunge zone.

The Wolfspar experience with low-frequency seismic source field data: Motivation, processing, and implications

The promise of fully automatic full-waveform inversion (FWI) — a (seismic) data-driven velocity model building process — has proven elusive in complex geologic settings, with impactful examples using field data unavailable until recently. In 2015, success with FWI at the Atlantis Field in the U.S. Gulf of Mexico demonstrated that semiautomatic velocity model building is possible, but it also raised the question of what more might be possible if seismic data tailor-made for FWI were available (e.g., with increased source-receiver offsets and bespoke low-frequency seismic sources). Motivated by the initial value case for FWI in settings such as the Gulf of Mexico, beginning in 2007 and continuing into 2021 BP designed, built, and field tested Wolfspar, an ultralow-frequency seismic source designed to produce seismic data tailor-made for FWI. A 3D field trial of Wolfspar was conducted over the Mad Dog Field in the Gulf of Mexico in 2017–2018. Low-frequency source (LFS) data were shot on a sparse grid (280 m inline, 2 to 4 km crossline) and recorded into ocean-bottom nodes simultaneously with air gun sources shooting on a conventional dense grid (50 m inline, 50 m crossline). Using the LFS data with FWI to improve the velocity model for imaging produced only incremental uplift in the subsalt image of the reservoir, albeit with image improvements at depths greater than 25,000 ft (approximately 7620 m). To better understand this, reprocessing and further analyses were conducted. We found that (1) the LFS achieved its design signal-to-noise ratio (S/N) goals over its frequency range; (2) the wave-extrapolation and imaging operators built into FWI and migration are very effective at suppressing low-frequency noise, so that densely sampled air gun data with a low S/N can still produce useable model updates with low frequencies; and (3) data density becomes less important at wider offsets. These results may have significant implications for future acquisition designs with low-frequency seismic sources going forward.

Extraction of diffractions from seismic data using convolutional U-net and transfer learning

Diffraction images can be used for modeling reservoir heterogeneities at or below the seismic wavelength scale. However, the extraction of diffractions is challenging because their amplitude is weaker than that of overlapping reflections. Recently, deep learning (DL) approaches have been used as a powerful tool for diffraction extraction. Most DL approaches use a classification algorithm that classifies pixels in the seismic data as diffraction, reflection, noise, or diffraction with reflection, and takes whole values for the classified diffraction pixels. Thus, these DL methods cannot extract diffraction energy from pixels for which diffractions are masked by reflections. We proposed a DL-based diffraction extraction method that preserves the amplitude and phase characteristics of diffractions. Through the systematic generation of a training dataset using synthetic modeling based on t-distributed stochastic neighbor embedding (t-SNE) analysis, this technique extracts not only faint diffractions, but also diffraction tails overlapped by strong reflection events. We also demonstrated that the DL model pre-trained with basic synthetic dataset can be applied to seismic field data through transfer learning. Because the diffractions extracted by our method preserve the amplitude and phase, they can be used for velocity model building and high-resolution diffraction imaging.

Seismic Velocity Model Building Using Neural Networks: Training Data Design and Learning Generalization

Data-driven artificial neural networks (ANNs) offer a number of advantages over conventional deterministic methods in a wide range of geophysical problems. For seismic velocity model building, judiciously trained ANNs offer the possibility of estimating high-resolution subsurface velocity models. However, a significant challenge of ANNs is training generalization, which is the ability of an ANN to apply the learning from the training process to test data not previously encountered. In the context of velocity model building, this means learning the relationship between velocity models and the corresponding seismic data from a set of training data, and then using acquired seismic data to accurately estimate unknown velocity models. We ask the following question: what type of velocity model structures need be included in the training process so that the trained ANN can invert seismic data from a different (hypothetical) geological setting? To address this question, we create four sets of training models: geologically inspired and purely geometrical, both with and without background velocity gradients. We find that using geologically inspired training data produce models with well-delineated layer interfaces and fewer intra-layer velocity variations. The absence of a certain geological structure in training models, though, hinders the ANN's ability to recover it in the testing data. We use purely geometric training models consisting of square blocks of varying size to demonstrate the ability of ANNs to recover reasonable approximations of flat, dipping, and curved interfaces. However, the predicted models suffer from intra-layer velocity variations and non-physical artifacts. Overall, the results successfully demonstrate the use of ANNs in recovering accurate velocity model estimates, and highlight the possibility of using such an approach for the generalized seismic velocity inversion problem.

Oriented NMO correction of VTI data in the absence of near-offset traces

Calculating an accurate seismic velocity model serves an important role in many seismic imaging techniques. The process of velocity model building is often time-consuming, specifically for anisotropic areas, where more than a single parameter is involved in the process. In the past few years, more time-efficient approaches have been considered to estimate seismic velocity as well as anellipticity parameters or heterogeneity factor using local event slopes. Nevertheless, some of these techniques are not practical due to curvature-dependency, or due to the lack of near-offset data. To address such limitations, we use a curvature-independent approach for normal-moveout correction as well as parameter estimation in vertical transverse isotropic media, which is based on local estimation of vertical traveltime using a shifted hyperbola approximation in the absence of near-offset data. The performance of the proposed approach is tested on synthetic and field common-midpoint gathers. It is also assessed in different signal-to-noise ratios and different missing-near-offset situations. Our findings are consistent with the results achieved by the previous methods that were not developed for sparse data.