... of hundreds of years) and the spatial scale, with laterally the representation of the regional aquifer to model the expansion of the pressure front following the CO2 injection, and vertically the inclusion of burdens to represent geomechanical effects. New simulation software, that enable directly coupled...

... (e.g., production profiles over 20-30 years). Such forecasts are often derived from numerical simulation models, in which parameters are inherently uncertain due to the limited knowledge available to accurately characterize the properties determining the behavior of the subsurface system. To take...

... presents a new dynamic mesh partition algorithm that adapts to the distribution of implicit/explicit cells, aiming to improve load balancing in compositional AIM simulations. The algorithm's effectiveness is demonstrated in several complex real models, where it obtains a close to even distribution...

... for coupled multiphysics simulations. The generalized MGR framework enables efficient solutions to linear systems arising from thermal and isothermal compositional flow, multiphase poromechanics, and fractured reservoir simulations. By integrating advancements into the hypre library, the extended MGR method...

... and computational cost. artificial intelligence model parameter covariance localization data assimilation fb localization deep learning machine learning-based localization assimilation machine learning ensemble tabular data matrix decision tree doi covariance estimation simulation regression...

... Abstract This study introduces an AI-integrated geology-engineering workflow for efficiently and accurately determining the ratio of effective fractures to hydraulic fractures in unconventional reservoirs. The workflow combines a boundary element-based hydraulic fracture simulator with a GPU...

... modeling & simulation ann model equation artificial intelligence simulation case accuracy reservoir simulation machine learning timestep size convergence engineer speedup activation function base case geoscientist & engineer simulation runtime fuzzy logic simulation...

... Abstract Network models have proved to be an efficient tool for building data-driven proxy models that match observed production data or reduced-order models that match simulated data. A particularly versatile approach is to construct the network topology so that it mimics the intercell...

... simulators with a novel convolutional-recurrent network (CNN-RNN) proxy. The proposed convolutional-recurrent neural network uses the governing equations of the coupled hydraulic-geomechanical process as the loss function. Initial conditions and spatial rock property fields are taken as inputs to predict...

... Abstract Commercial reservoir simulators have traditionally been optimized for parallel computations on central processing units (CPUs). The recent advances in general-purpose graphics processing units (GPUs) have provided a powerful alternative to CPU, presenting an opportunity...

... frameworks, such as control system theory, machine learning theory, real-time dynamical modeling, and high-performance computing to enhance current and newly developed algorithms for reservoir simulation. Motivation Abstract Integrated reservoir studies for performance prediction and decision-making...

... Reservoir simulation is an important tool to model and understand a reservoir. A collection of static and dynamic subsurface data constitutes input to a subsurface modelling tool and a numerical flow simulator. A workflow combining numerical simulations, optimization, history matching...

... of a nonlinear partial differential equation (PDE), within the Operator-Based Linearization (OBL) simulation framework, and discover the physical space for a physics-based proxy model with reduced degrees of freedom. In our methodology, observations from a high-fidelity model are utilized within a supervised...

... Abstract Commercial reservoir simulators have traditionally been optimized for distributed parallel execution on Central Processing Units (CPUs). Recent advances in Graphics Processing Units (GPUs) have led to the development of GPU-native simulators and triggered a shift towards a hardware...

... (1) x ∗ = arg ⁡ max x ∈ X f ( x ) , Abstract We present a framework of the application of Bayesian Optimization (BO) to well management in geological carbon sequestration. The coupled compositional flow and poroelasticity simulator, IPARS, is utilized...

... droplets or solid particles. Theoretical derivation and numerical simulations with and without relative motions between continuous and disperse phases are examined first. The results illustrate that the shock wave structures and flow properties associated with the multiphase gas flows are different than...

... results support a priori stability analyses. equation of state stress method geomechanics stability hydraulic fracturing fracture aperture simulation stabilization term finite element method sequential method artificial intelligence flow problem fracture length boundary condition...

... the simulation efficiency by incorporating the equilibrium constraint equation ( K I e q = K c r ) into the Newton-Raphson process. We first illustrate the idea using single tip fracture propagation, then extend it to the multiple fracture propagation scenario. time-continuation...

... numerical simulator, we investigated the effects of viscous fingering, perforation design and stage period on the acid etching process. Compared with single-stage acid injection, multi-stage alternating injection of pad and acid fluids leads to narrower and longer acid-etched channels. Introduction...

...Introduction Abstract Reservoir simulation is the most widely used tool for oil and gas production forecasting and reservoir management. Solving a large-scale system of nonlinear differential equations every timestep can be computationally expensive. In this work, we present a two-phase...