... of the Rayleigh tunnel surface wave in the coal layer. Therefore, the S-wave Theory and method velocity model can be obtained from its group or phase velocity dispersion curve. The applicability of this method is From a geophysical point of view, the main factors demonstrated with the data from a 2-m thick coal...

... machine learning applied geoscience waveform inversion warner artificial intelligence awi exploration geophysicist 10 reflection waveform inversion formulation reservoir characterization field data velocity model inversion rwi dataset umpleby synthetic dataset upstream oil...

... category for source location methods is based on the back-propagation methods, which helps reduce the wavefield back-propagation of the observed recordings uncertainty of source locations. With the generated source with a reasonably accurate velocity model (Fink, 2006). cloud imaging, the fractured volume...

... prospects. In order to image the very complex salt flanks, accurate 3D velocity models for imaging is required. Experience from TopSeis acquisition both in the Barents Sea and the North Sea has provided sufficient evidence to continue a similar acquisition setup for recording of the seismic wavefield...

... additional wavefield storage or re-computation. In this paper, we propose a method to recover the macro-velocity model using the monochromatic traveltime sensitivity kernel (MTSK) with the random boundary condition. Due to the significantly reduced memory occupancy and computational cost, the application...

... physical that require more modeling realizations. time. The resulting FWI objective function enables the solution of two parameters, velocity model and time- We introduce a novel method that minimizes the data fitting warping extension, in a single optimization problem, which between the synthetic...

... Seismic time-lapse (4D) surveys have been widely used to quantitatively monitor the geophysical property changes within hydrocarbon reservoirs due to production effects. Full-waveform inversion (FWI), which has become one of the most reliable tools for velocity model building (VMB), is a natural...

... Model error is endemic to full waveform inversion (FWI). Bayesian moment tensor inversion is an example of a linear inverse problem that can be heavily affected by errors in the velocity model. The choice of misfit function plays a crucial role in mitigating the effects of these errors. We...

... and Dask. We demonstrate a large-scale 3D FWI using 1000 VMs/nodes on Azure, where Hyperwavve uses distributed containerized processes to successfully invert for the full 3D (20x20x5 km 3 ) overthrust velocity model. We also further validate that our Hyperwavve can distribute FWI work onto 6000 (or more...

... structures are successfully recovered with the predicted low-frequency components. neural network applied geoscience prediction reservoir characterization low-frequency component training set machine learning upstream oil & gas reflection event expanded abstract velocity model workflow...

... shot carpet velocity estimation workflow decimation reservoir characterization production model velocity model exploration geophysicist 10 upstream oil & gas applied geoscience full-waveform inversion deep water play dataset obn survey sparse-node geometry santos basin yannick...

... calibration cube study area time slice artificial intelligence geologic structure upper indus basin reservoir characterization applied geoscience well velocity velocity field workflow average velocity velocity function velocity model seismic velocity gas development company ltd...

... The velocity model in downhole microseismic monitoring plays a vital role in accurate mapping of the hydraulic fracturing image, but the conventional velocity optimization method by the perforation shot introduces non-negligible event location errors when the geological formations are complex...

... and geologic interpretation. We describe an integrated multidisciplinary approach that incorporates broadband signal processing of the 2831 sq. km of narrow-azimuth data in the area, multi-scale common image point tomography and full-waveform inversion velocity updates, rock physics-based velocity modelling...

... sensitive to the inaccuracy of the velocity model due to cycle skipping. Recently, FWI with search-space extension tackles this sensitivity issue by solving the wave equation with a data assimilation. When the wavefields and the source signatures are jointly estimated with this approach, the extended wave...

... the complexity of the salt and subsalt velocity models. Recent advances in full-waveform inversion (FWI) algorithms combined with a newly acquired, ocean bottom node (OBN) data set have ushered in a fundamental shift in velocity model building and imaging at Shenzi as we move away from mostly interpretation...

... to estimate common rock-physics attributes that highlight the potential presence of a gas-bearing sand reservoir. reservoir characterization applied geoscience velocity model target area target-oriented elastic full-waveform inversion upstream oil & gas expanded abstract geophysics procedure...

... using seislet transform. shaping regularization (RSFWI) is stable and effective to The local dip information is provided by migration-mode recover a background velocity model. The final inverted gradient. Therefore, the regularization require little velocity model is more accurate than the conventional...

... Velocity model building is an essential step in seismic exploration, which runs through the whole process of seismic data acquisition, processing, and interpretation. The velocity information is conventionally obtained by iterative optimization methods such as full-waveform inversion...

... artificial intelligence troy thompson velocity model inversion preconditioner applied geoscience convergence mrinal sinha gary hampson l-bfg gradient Reflection FWI with an augmented wave equation and quasi-Newton adaptive gradient scheme James McLeman*, Tim Burgess, Mrinal Sinha, Gary Hampson...