... linear systems in multiphysics applications. fluid dynamics subsurface storage geologist reservoir simulation simulation iteration preconditioner flow in porous media reservoir characterization scalability application reservoir geomechanics multiphase flow green line show average...

... Abstract This study introduces an efficient deep learning-based reduced-order modeling (ROM) approach for reservoir history matching (HM) applications. The approach builds on the existing Embed-to-Control and Observe (E2CO) framework, which integrates an autoencoder for projecting state...

... . Upscaling of capillary trapping under gravity override: application to co2 sequestration in aquifers . In SPE Improved Oil Recovery Conference? , pages SPE-113496 . SPE . Juanes , R. and Patzek , T. W. 2003 . Relative permeabilities in co-current three-phase displacements with gravity...

... Abstract Using network simulation models in closed-loop reservoir management has become increasingly popular. Field applications across different asset classes have highlighted their versatility and value. These models consist of approximate or coarse simulation grids that align with wellbore...

... reservoir characterization simulation grid waterflooding flow in porous media application surrogate model mathematics of computing reservoir simulation artificial intelligence permeability field graph model information spe reservoir simulation conference equation connection distance...

... by introducing an imbalance criterion. This criterion triggers the application of the algorithm from Section 2 to generate a new partition using Equation (8) to calculate weights. The goal is to obtain an even distribution of equations into the subdomains, rather than cells. Let N eq,i be the total number...

... In this overview paper, we first review the foundations of the optimization framework and its stochastic gradient estimation scheme (section Theoretical background). Next, we also describe relevant aspects of its implementation in EVEREST and present various examples of its application to design...

... reservoir property application sand layer production data enhanced recovery observation data hm result error range artificial intelligence gpsnet model flow network pseudo well node uncertainty parameter Introduction Insights from reservoir simulation models have often been used...

... (and other quantities) to rank and select representative models for high, medium, and low performance scenarios that can be used for full field simulations. In this paper we present an application of the multiscale sequential fully implicit (MS SFI) framework to simulate extremely complex high-resolution...

... to cohesive mechanical healing. fluid dynamics flow in porous media permeability upstream oil & gas enhanced recovery scenario reservoir simulation precipitation experiment inlet selective inorganic precipitation injection deposition application united states government reservoir...

... equation cpr-addwell application newton iteration coupling solver operator petroleum engineer Introduction Modern reservoir simulations face increasingly complex physical models and highly complex interactions between wells and the reservoir. They typically adopt the fully implicit method...

... iteration equation neural network machine learning tchelepi mesh algorithm converge klemetsdal reservoir simulation artificial intelligence approximation utulsa application solver expedite reservoir simulation comput Introduction Solution of the nonlinear reservoir simulation...

... neural network machine learning upstream oil & gas artificial intelligence deep learning reservoir characterization journal united states government reservoir geomechanics differential equation accuracy porous media approximation physics-informed neural network application simulation...

... Abstract In this paper, we present an efficient inverse modeling framework for energy transition applications. The key feature of this framework is a combination of adjoint gradients and Operator-based Linearization (OBL) technique to achieve high efficiency in inverse modeling based on forward...

... of the objective function may be too expensive to compute for realistic applications in the absence of the implementation of the adjoint method. In this paper, we develop a quasi-Newton method based on the stochastic simplex approximate gradient (StoSAG), which requires only objective-function values. We have...

..., maintainable code with applicability across a wide range of models. Different parts of a reservoir simulator benefit from different approaches. A modern, object-oriented simulator requires components to handle initialization, property calculation, linearization, linear solver, well and aquifer calculations...

... results have been achieved on the field level and good matches have also been observed for key producers. In addition, the history matching consumes mere 4 hours to finish 1,100 simulation jobs. The successful application of the GPSNet to this waterflood field demonstrates a promising workflow that can...

..., followed by application of the method to a travel-time tomography inverse problem to investigate its model updating performance. neural network resolution architecture deep learning machine learning parameterization united states government artificial intelligence autoencoder upstream oil...

... the application of distance-based localization during data assimilation with the Ensemble Smoother with Multiple Data Assimilation (ES-MDA). The performance of the proposed method is investigated in a synthetic benchmark problem with realistic settings. We evaluate the methodology with three variants...

... calculation. Previous models used the conventional Peng-Robinson equation of states (PR EOS), which becomes inaccurate when the pore diameter reduces to the scale of nanometers. With PR-C EOS, fluid characteristics can be accurately modeled under nano-scale conditions, making our model applicable to shale...