... of uncertainty parameters and the corresponding simulation data across all wells. The system utilizes recent advances in deep learning based on deep neural networks, convolutional neural networks, and autoencoders to create machine-learning-based proxy models that predict production and injection profiles...

... memory consumption, which makes the method suitable for images with large size. The paper provides a way to develop an alternative approach of PNM simulation method for permeability prediction from CT images. upstream oil & gas neural network fluid dynamics deep learning permeability asia...

... the given input and output parameters. In this study, symbolic regression (SR), decision tree (DT), random forest (RF), extremely randomized trees (ERT), adaptive boosting (AdaBoost), gradient boosting (GB), extreme gradient boosting (XGBoost), artificial neural network (ANN), and deep neural network (DNN...

... government machine learning linear regression empirical correlation journal coefficient composition bubble point pressure proceedings neural network petroleum technology crude oil deviation reservoir interactive multivariate linear regression INTRODUCTION Standing (1947) was the first...

... keeping the parametrization of uncertainties as practical as possible. reservoir optimization problem history matching neural network upstream oil & gas reservoir simulation artificial intelligence machine learning boundary evolutionary algorithm north kuwait criteria asia government...

... engineer neural network machine learning concentration fno kaolinite co 2 permeability tariq exhibition simulator subsurface storage climate change society mole fraction abdulraheem mineral prediction anorthite Introduction Mineral trapping is recognized as the most secure carbon...

... reservoir simulation production monitoring machine learning reservoir surveillance reservoir characterization pvt measurement neural network scaling method reconstruction application discriminator petroleum engineer saturation algorithm augmentation equation generator super-resolution...

... The third step is "creating an AI-physics dataset" . Training the Deep Neural Network (DNN) with available data is one of the main steps in our workflow. The data comes from the simulation results, the static data (such as the well geometry, well location, and static grid properties...

... accurately predict the AOP curve for a combination of reservoir fluids and injection gases, as the long as the injection gas composition remains within the range tested experimentally. asphaltene inhibition upstream oil & gas neural network oilfield chemistry artificial intelligence uae...

... asia government calculation neural network machine learning upstream oil & gas china government pvt measurement artificial intelligence prediction molar composition reduction diagram accuracy simulation application fraction mole fraction procedure sour ga composition...

... In the following we briefly describe the network architecture, choice of activation function, loss function and training/testing setup to adequately capture the correlation between injection parameters and cumulative recoveries. The resulting dense neural network then serves as a function...

... analysis. For generating the related proxy models, polynomial regression, and radial basis function (RBF) neural networks were investigated. Subsequently, the DECE-based and PSO-based optimization methods were employed to examine the effect of chemical design parameters such as smart water (Mg 2...

... applications have been implemented using convolutional neural networks (CNN). These models act like finite-dimensional operators, which, using simulation data, can learn mappings from the input space (e.g. permeability, porosity, injection rate) to output space (e.g. saturation, pressure). Zhu and Zabaras...

...-physics coupled nature. Therefore, an efficient optimization framework is critical for the management of EGS. We develop a general reservoir management framework with multiple optimization options. A robust forward surrogate model f l is developed based on a convolutional neural network...

... history match with all the extra inputs and forecast; and optimizing the development with all the input parameters within a short timeframe is always a challenge. The process employed in this approach was based on deep learning artificial neural networks (ANN) coupled with numerical simulators and along...

... of the solution is represented by powerful machine learning methods such as Generalized Additive Models (GAM), Gradient Boosting, and Convolutional and Recurrent Neural Networks. Neural Networks and Gradient Boosting methods are very popular machine learning techniques. However, in this work, it is demonstrated...

... and can be used as a quick assessment tool to evaluate the long term feasibility of CO 2 movement in fractured carbonate medium. asia government upstream oil & gas petroleum engineer neural network artificial intelligence complex reservoir denmark government deep learning hydraulic...

... into the accuracy and prediction performances of these machine learning-based proxy models for 3D oil-water systems as well as their efficiency in nonlinearly constrained production optimization for waterflooding applications. upstream oil & gas artificial intelligence gradient neural network npv...

... (Northern Oman). Thereafter, the supervised probabilistic neural network (PNN) and linear regression method were undertaken to detect an additional channel distribution. The relationship of high porosity with low acoustic impedance appeared mostly in the channel facies which reflects good reservoir quality...

... from Continuity), distance from Top Mishrif. In the light of these results, the most meaningful parameters have been used as input data for a Neural Net Process ("Supervised Neural Network") utilizing the Supervised dataset both as a Trained dataset (70%) and as a Verification dataset (30...