... of subsurface property maps that enables local updates to property distributions at different scales. The deep learning model consists of a convolutional neural network architecture that learns successive mapping across multiple scales, from a coarse grid to increasingly finer grid representations. Once trained...

... intelligence hoteit deep learning norway government prediction bayesian mcmc bayesian inversion markov chain monte carlo kwak spe annual technical conference history matching neural network information accuracy geothermal reservoir bilstm Introduction A fast and large-scale transition...

... the efficiency of underground hydrogen storage. corrosion management h2s management riser corrosion neural network materials and corrosion upstream oil & gas structural geology production chemistry pipeline corrosion deep learning oilfield chemistry reservoir characterization flowline...

... perceptron (MLP) is trained to predict whether the fluid is in single-phase or two-phase condition. The equilibrium ratios are estimated using a physics-informed neural network (PINN) in the flash calculation. The application of ML techniques accelerates the CPU time by two orders of magnitude without losing...

... upstream oil & gas artificial intelligence autoencoder latent representation dimension neural network machine learning reduction permeability deep learning reservoir characterization ensemble reconstruction implementation realization petroleum science application reparameterization...

... reduced physics models into a neural network architecture by utilizing two different approaches. In the first approach, the reduced physics model is used for pre-processing to obtain approximate solutions that feed it into a neural network as input. This physics-based input feature can reduce the model...

... 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 the variation of pressure and stress fields. A customized convolutional filter mimicking the higher-order...

... two novel components: (1) augment the state-space to yield a bi-linear system, and (2) an autoencoder based on a deep neural network to linearize physics reservoir equations in a reduced manifold employing a Koopman operator. Recognizing that reservoir simulators execute expensive Newton-Raphson...

... idea of PIML approaches is to encode the underlying physical law (governing equations, boundary, source and sink constraints) into the deep neural network as prior information. The capability of the PIML method in handling reservoir engineering boundary including no-flow, constant pressure, and mixed...

..., approximating the progression of the system from one timestep to the next using a linear transition model, and finally projecting the system back to high-dimensional space using the encoder-decoder. To guarantee mass conservation, we adopt the Finite Elements Mixed Formulation in the neural network's loss...

... Abstract We present our progress on the application of physics informed deep learning to reservoir simulation problems. The model is a neural network that is jointly trained to respect governing physical laws and match boundary conditions. The methodology is hereby used to simulate a 2-phase...

... the Peng-Robinson EOS has only one root, which is often the case at reservoir conditions. The proxy fugacity model was trained by artificial neural networks (ANN) with over 30 million fugacity coefficients based on the Peng-Robinson EOS. It accurately predicts the Peng- Robinson fugacity coefficient...

... to traditional methods. This work aims to build an image-to-value model based on convolutional neural network to model the nonlinear mapping between the high-resolution image of detailed DFM as input and the upscaled reservoir simulation model as output. The reservoir simulation model (herein refers to the dual...

... a geological parameterization that entails principal component analysis combined with a convolutional neural network (CNN-PCA) and a flow surrogate that uses a recurrent residual-U-Net procedure – into three different history matching procedures. The history matching algorithms considered are rejection...

... of flow-based upscaling is limited due to its high computational cost. In this work, we parametrize the fine-scale fracture geometries and assess the accuracy of several convolutional neural networks (CNNs) to learn the mapping between this parametrization and the DPDP model closures such as the upscaled...

... iteration gradient-based optimization egg model model evaluation gradient neural network exact gradient approximate gradient es-mda reynolds automatic differentiation equation Introduction The computational cost of evaluating a reservoir's response to a given set of parameters and control...

... augment it when new situations are encountered, so the system becomes more effective as it is exposed to more data. thermal method modeling & simulation reservoir simulation enhanced recovery neural network simulation feature artificial intelligence steam-assisted gravity drainage...

... upstream oil & gas artificial intelligence reservoir simulation node displacement reservoir characterization neural network constraint contact traction time step size matrix rupture equation onset nucleation boundary geophysical research hydraulic fracturing fluid dynamics...

... efficiency of the calculated statistics for the update step. neural network autoencoder neural network architecture artificial intelligence reservoir simulator representation model realization dataset machine learning upstream oil & gas lsda ensemble latent variable model latent...

... history matching for subsurface flow modeling. flow in porous media neural network history matching upstream oil & gas artificial intelligence deep learning dimensionless time posterior distribution high-fidelity model workflow latin hypercube long-short term memory accuracy...