... 0.82 0.25 0.19 45.12 CAE-ANN 0.64 0.19 0.07 39.95 SAE-ANN 0.52 0.11 0.09 29.38 Results clearly show that the SAE-ANN autoencoder approach outperforms the other methods as it has the least MAPE error overall. This is because the dataset being predicted is highly dimensional...

... adopted in predictions affected by various factors. This paper presents a step-by-step workflow of applying a ML approach to develop a heterogeneous permeability prediction model from the CT images of core samples. In this work, over ten thousand 3-D sub-image were randomly extracted from the CT images...

... Machine learning can also be helpful to improve NMR models and predict petrophysical properties for carbonate rocks such as porosity, permeability, and irreducible water saturation. To apply ML, the selected algorithm is trained on the available dataset to establish a relationship between...

... and perform inspectional analysis. When collinearity (correlations) between the predictors expressing a linear relationship occurs, the independent data will not predict the dependent variable. Data visualizations aid in quickly identifying such problems. Kernel density plots of the data are displayed...

... simulators. In this work, we have developed a DL approach to effectively predict the dissolution and precipitation of various important minerals, including Anorthite, Kaolinite, and Calcite during CO 2 injection into deep saline aquifers. We established a reservoir model to simulate the process...

... of the wetting fluid, calculated by the implicit pressure and explicit saturation (IMPES) method, where water pressure is the implicit variable, and water saturation is the explicit variable. Abstract Complete physics-based numerical simulations currently provide the most accurate approach for predicting...

... an AI-physic model" . Based on the data analysis in the Meera Centrum, it was decided to set up three different DNNs for the training behavior of the oil, gas, and water production profiles. The sixth step is "Blind Test Prediction" . The parameter tuning and feature selection for a DNN...

... 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...

... samples or reduced by removing redundant samples (simulation runs). Consequently, the hybrid neural approach also provides a clear picture of which simulation runs (or samples) are more conducive to optimal recovery predictions for an effective strategy to sample the high dimensional WAG parameter space...

...: 1) Rock physics modelling and shear sonic prediction 2) Invasion correction and production effect correction of elastic logs 3) Seismic feasibility analysis to define seismic facies and 4) Six angle stacks optimally defined to preserve AVO/AVA signature followed by AVO/AVA compliant post-stack...

... of the confinement of plumes at each potential storage site. The accurate prediction of the flow, geochemical, and geomechanical responses of the formation is essential for the management of GCS in long-term operations because excessive pressure buildup due to injection can potentially induce fracturing of the cap...

... the adoption of Machine Learning (ML) approach to identify new Behind Casing Opportunities (BCO) in two brown fields (B and S) offshore East Malaysia. A multi-stage field-based ML models were developed based on selected wells and consequently used to predict reservoir characteristics in completed wells...

... This manuscript is structured as follows. In Section 2, we introduce the physics problem and the reservoir simulation results. In Section 3, we illustrate the details of the forward surrogate model to predict the temperature field and its prediction performance. In Section 4, different methods...

... simulator prediction Run the simulations The AI simulator hybrid engine couples its embedded 3D, 3-phase numerical reservoir simulation engine with an innovative time-series deep neural networks leading to a super-fast reservoir simulator with proper history matching and forecast capabilities...

..., while it often suffers from nonphysical solutions and unexplainable models. The presented method holds the properties of explainable regression models while providing powerful predictability capabilities within material balance constraints. By no means does it try to replace the reservoir simulation...

... of the surrogate models. The developed workflow showed superior performance by giving AAPE less than 5% and R 2 more than 0.95 between ground truth and predictions of the state variables. The proposed Deep Learning framework provides an innovative approach to track CO 2 plume in a fractured carbonate reservoir...

... and optimal results obtained. One of the proxy models is embed to control and observe (E2CO), a deep learning-based model, and the other model is a kernel-based proxy, least-squares support-vector regression (LS-SVR). Both proxies have the capability of predicting well outputs. The sequential quadratic...

... , is given by Eq. (10) . Once the phase behavior is determined and physical properties are obtained from PR-VT EOS, the dynamic viscosities of phases are predicted via LBC viscosity correlation. We adopt the standard format to calculate the viscosity of mixture, μ , as Eq. (6) . LBC viscosity...

... to guide new wells location and trajectory. Actually, two proof of concept case histories have demonstrated the reliability of this approach. The newly drilled wells, with optimized paths according to these prediction-maps, have intercepted the desired karst intervals as per the subsequent image log...

... as intrinsic noise. Consequently, using a machine learning-based method that can resolve both the temporal and spatial non-linear variations has advantages over a pure engineering model. The approach followed provides a long short-term memory (LSTM) network-based methodology to predict BHP and temperature...