... of a seismic attribute that may be significant in seismic fault interpretation or a seismic fault attribute is treated as an image segmentation problem and using different deep learning (DL) architectures. For doing this, the researchers mainly concentrate on applying cutting-edge DL architectures in computing...

... and data from the Duvernay Formation as the test data. The method successfully predicts TOC-rich formations, in agreement with independently obtained core-measured TOC values. upstream oil & gas unconventional resource economics deep learning complex reservoir formation neural network...

... Recently, first arrivals picking is treated as an image segmentation problem and deep learning (DL) algorithms have been successfully used to pick the first arrivals of seismic shot gathers. Researchers have demonstrated that cutting-edge DL architectures have the potential to improve...

... abstract international inversion geophysics reservoir characterization exploration geophysicist energy 10 geophysical prospecting extended abstract full-waveform inversion kalita expanded abstract deep learning Second International Meeting for Applied Geoscience & Energy 10.1190/image2022...

... We employ the deep learning approach to build a high-fidelity surrogate for fast modeling of electromagnetic well logging measurements in high-dimensional complex formations. Due to the limitation of the computational resource, real-time applications are primarily dependent on 1D electromagnetic...

... The lack of low-frequency data components has been a major obstacle in FWI applications for velocity model building. Many theoretical approaches have been proposed to extrapolate low-frequency components. Progressive transfer learning was proposed to solve the problem by using a deep learning...

... that the neural network can capture spatial correlations at different scales and thus can introduce regularization in our inverse problem. The regularization is enough to mitigate the cross-talk problem in elastic FWI and also produce good results in areas with low illumination. deep learning reservoir...

... on a field data. The research shows that the prediction results are accurate in the data with medium and high SNR, and the network model can quickly pick the time-velocity sequence, improve the efficiency of velocity spectrum picking. spectrum reservoir characterization detection deep learning...

... In this paper, we will explore a flexible and versatile deep learning enhanced (DLE) multi-physics joint inversion framework and discuss its applications and prospects. Unlike conventional end-to-end networks that map directly from the data domain to the model domain, this DLE framework...

... a procedure to generate highly realistic, synthetic GPR images for this neural network to accurately produce high-resolution images for field data applications in different scenarios. Synthetic and field data examples show the good generality and fidelity of our method. deep learning grid number...

... for the exploration of low-relief structures. The inversion of the large TEM dataset is carried out with a hybrid inversion approach combining deep learning and physics-driven least-squares inversion. The procedure provides a sharp mapping of the shallow BoS resulting in the improvement of the seismic images...

... information to generate synthetic data from the subsurface AI distribution. We also add Bayesian layers to the first stage of the network to evaluate the model errors. The proposed probabilistic approach to deep learning allows one to estimate the uncertainty of the obtained parameters, which enhances...

... models. We proposed a deep learning framework, trained with field data-driven synthetics and then combined with full-waveform inversion, to estimate the near-surface velocity model with reversals. deep learning international reversal artificial intelligence machine learning upstream oil...

... setup but on a simplistic geological model. Of which we observe an improvement in the inference results as well as new observations regarding the subsurface, which had not been under consideration. This work provides insights into using deep learning as a method to refining our understanding...

... as a fully automatic facies predictor rather than a baseline interpretation tool. neural network prediction deep learning machine learning upstream oil & gas artificial intelligence facies international american association exploration geophysicist dataset reservoir characterization...

... marine and land. Deep learning allows achieving a significant speed-up compared to the conventional method while preserving an acceptable quality of the results. deep learning reservoir characterization workflow estimation enhancement upstream oil & gas artificial intelligence wavefront...

... separating reflections and diffractions in complex data although no field data was part of the training. deep learning reservoir characterization application diffraction separation wavefield upstream oil & gas artificial intelligence gpr diffraction separation neural network machine...

... and accurately identify phase arrivals reduces the time required to process passive seismic data. upstream oil & gas artificial intelligence international neural network machine learning deep learning reservoir characterization applied geoscience workflow algorithm phasenet exploration...

..., demonstrating super image quality in in-vivo diagnostic applications, with frame rates that are comparable to those of commercial ultrasound scanners. transducer health & medicine upstream oil & gas artificial intelligence deep learning reservoir characterization imaging real time system...

... intelligence operator continuation machine learning fourier neural operator herrmann deep learning reservoir characterization imaging seismic imaging velocity continuation international conference fno reflector fomel init american association neural network quantification geophysics...