... methods reservoir geomechanics production control reservoir characterization machine learning geological subdiscipline climate change gru-fno dataset co 2 representation information fourier neural operator boundary condition ground truth sequence tversky loss saturation prediction...

... scenario cff equation structural geology flow in porous media geological subdiscipline autoencoder manzoni plate tectonics neural network machine learning modeling dataset journal manifold fluid dynamics deep learning artificial intelligence order model contribution dl-rom...

... dynamics reservoir simulation machine learning pod-rom preconditioner physics solver performance basis function migration period basis vector equation solver and run-time speedup result evaporation model cpr-amg diffusion Introduction Model reduction techniques are essential...

... compared to the simulated variables generated by a high-fidelity simulator, offering valuable insights into its performance. history matching neural network deep learning assimilation geologist reservoir simulation machine learning prediction state variable production rate well output...

... Abstract Current reservoir simulators solve Advection-Diffusion-Reaction equations on unstructured grids to a high degree of accuracy but are computationally expensive to use in history matching, optimization and uncertainty quantification workflows. We propose a novel machine learning...

... Abstract We propose a novel framework based on machine learning methods for tabular data and a distance-free localization to enhance the covariance estimations in an ensemble data assimilation. The main goal is to enhance the data assimilation results by mitigating loss of variance due...

... in porous media realization onur machine learning case 10 100 geologist realization 1 well control production optimization neural network optimization spe10 model e2co prediction nonlinear state constraint realization 5 denote nguyen and onur pressure distribution objective function...

... fine-scale solution. We apply the proposed method and accurately reconstruct the fine-scale solution of two- and four-component problems in heterogeneous, two-dimensional reservoir models. artificial intelligence neural network operator machine learning conservation equation interface deep...

... problem complex reservoir modeling & simulation structural geology production monitoring rock type machine learning numerical simulation reservoir surveillance schiozer production control wag-co 2 matrix cycle size artificial intelligence chemical flooding methods snapshot dynamic...

... artificial intelligence production control prediction singh reference model ensemble data-space inversion dimension geology reservoir surveillance machine learning dsi framework szklarz and barros production rate forecast procedure injection rate scenario posterior Introduction Oil...

... across both temporal and spatial domains. The temporal discretization scheme, in addition to other factors such as reservoir model's complexity, influence the Newton iterations and the overall runtime of the numerical simulation. This work capitalizes on machine learning approach to predict the optimal...

... management reservoir online network target network agent realization geology machine learning optimization drilling scheduling olympus challenge computational geoscience field development planning soft-update mechanism q-value geological property oil production experiment Introduction...

... machine learning production monitoring configuration reservoir surveillance power plant optimization problem production control production temperature geothermal power plant stand-alone power plant decision parameter bottom hole temperature surrogate model hybrid power plant geothermal...

... artificial intelligence reservoir surveillance machine learning production monitoring permeability field reservoir characterization geologist modeling & simulation production control production data annual technical conference and exhibition water saturation change datta-gupta streamline...

... reservoir simulation artificial intelligence machine learning geology scientific computing reservoir characterization optimizer geologist optimization problem reservoir geomechanics geological subdiscipline florez flow in porous media jacobian duchon spline approximation evolutionary...

... convergence and higher accuracy. The SAOR in this paper is configured with different types of (DoE), two adaptive sampling methods and two machine learning models: Gaussian Process (GP) and Adaptive Neuro-Fuzzy Inference System (ANFIS). This enables the evaluation of multiple physics-informed AI...

...Introduction As noted earlier, the main interest of this study is estimating fine-scale reservoir simulation results using upscaled reservoir simulation results. Machine learning methods have been applied to correct errors from upscaled model simulation results. Trehan and Durlofsky (2018...

... knowledge, our new self-learning time-step selector is the first to be based on a statistical approach. subsurface storage reservoir simulation geology artificial intelligence time step iteration reservoir surveillance machine learning production control geologist modeling & simulation...

... algorithm production data local calibration streamline-based three-phase history matching geology modeling & simulation reservoir characterization calibration gtti misfit equation of state enhanced recovery machine learning inversion permian basin reservoir heterogeneity maintain...

... history matching using adjoint gradients while still using industry-standard commercial reservoir simulators. history matching optimization problem geologist reservoir simulation geology evolutionary algorithm machine learning adjoint gradient permeability equation conference...