... a practical workflow capable of introducing stochasticity into convolutional neural network (CNN) based 3D rock property estimation from angle-stack seismic and sparse wells. The workflow consists of four major steps, including (i) building a large-scale structural model (LSSM), (ii) generating prior property...

... geologist mechanism focal mechanism solution neural network p-wave first-motion polarity machine learning polarity applied geoscience & energy 10 deep learning reservoir characterization mechanism solution chen plate tectonics artificial intelligence focal mechanism architecture west...

... Five-dimensional (5D) seismic data reconstruction is a crucial step to improve seismic imaging. We introduce a deep complex-valued neural network for constructing an unsupervised frequency–space domain deep learning framework to reconstruct each frequency component of 5D seismic data. We apply...

.... Combining multi-frequency or multi-azimuth faults is another application for this technique. geologist artificial intelligence petroleum geology neural network geological subdiscipline interpretation machine learning fault prediction prediction applied geoscience & energy 10 reservoir...

... and 3D neural networks (2D and 3D GAP) were developed to clean seismic gathers along offset and time/depth directions. However, the issues of low-amplitude and steep-dip washout persist and make the result less reliable. To mitigate these issues, we use AVC (amplitude-based scaling) and gather stack...

... with margin labels, the proposed method can achieve better performance than the label. Meanwhile, the co-evolution of neural networks and data is utilized to annotate more data and achieve better generalization. Experiments demonstrate that the proposed method has obtained better results than the labels...

... transformer initial model neural network seismic data geology information reservoir characterization interpolation geophysics applied geoscience & energy 10 acquisition american association architecture deep learning yangkang chen 1 Pushing the limit of 5D interpolation using deep learning...

... Recent advances in deep learning and computer vision have resulted in giant leaps in automating some of the cumbersome oil and gas exploration and production operations. Deep convolutional neural networks have been widely used for seismic interpretation tasks including detection, classification...

... We develop a deep neural network-based method for automatic baseline correction (ABC-Net) of spontaneous potential (SP) logs to overcome the challenge of SP log deviation and trend accumulation with depth due to salinity and temperature effects. Our method utilizes a deep convolutional U-Net...

..., this is the first example of an elastic FWI of field data without an initial model. geologist artificial intelligence inversion petroleum geology machine learning economic geology zhang geological subdiscipline expanded abstract applied geoscience neural network reservoir characterization full...

... dispersion inversion workflow. Firstly, we use parameters with high sensitivity to create a small-scale dataset to train a neural network with a residual structure. By imposing monotonicity constraints on the model output, we achieve rapid and effective simulation of dispersion using less than 5% of the data...

... at the same time, so as to realize the first break picking stably. Finally, we use field data demonstrate the effectiveness of the proposed first break picking method. geologist artificial intelligence correction geology template deep learning reservoir characterization nltd neural network...

... on the available data while avoiding their inherent shortcomings. geologist geology artificial intelligence geological subdiscipline borehole data neural network reservoir characterization dataset geophone applied geoscience & energy 10 american association hydraulic fracturing machine...

... in porous media geologist reservoir simulation equation neural network fluid dynamics geology artificial intelligence neural operator coupling machine learning gpu-accelerated full-physics simulator applied geoscience & energy 10 fourier neural operator-based surrogate model enhancing...

..., a convolutional neural network (CNN) is trained to reconstruct the near offset gap of source-over-cable common depth point gathers acquired in the North Sea, yielding low reconstruction error on unseen gathers. The trained network is then tested on a source-over-cable dataset acquired in the Barents Sea...

... In this research, we combine data-driven and physics-driven strategies to train a physics-informed neural network for the simulation of electromagnetic wave propagation. By leveraging the constraints from the partial differential equation, the pre-trained network is able to efficiently predict...

... the importance of incorporating both spatial and temporal dependencies for more accurate boundary detection and lithostratigraphic unit classification. The proposed model, in particular, outperforms traditional convolutional neural networks by providing more accurate predictions and effectively identifying...

... improvement for at lower concentrations of 0.1wt%. In addition, five mathematical models were constructed using artificial neural network (ANN) to predict the rheological properties of the nano-modified drilling fluids based on their composition at 120 ˚F and atmospheric pressure. The models were evaluated...

... improves the resolution processing accuracy of thin deep carbonate reservoir, which can be popularized and applied to high-resolution imaging and high-precision prediction of thin reservoirs. processing method geological subdiscipline geology reservoir characterization neural network machine...

... of the Convolutional Neural Network (CNN) trained with the proposed methodology on synthetically generated data and on field datasets. geologist artificial intelligence discrimination geology reservoir characterization deep learning machine learning seismic event multiple model neural network...