... and the error was 3.8% for ANN, 4.5% for ANFIS, 4.3% for SVM, and 3% for DT for the tubing model. machine learning flow rate pressure drop neural network actual pressure drop Mohaghegh AAPE Artificial Intelligence correlation testing data flow line model low error SVM multiphase flow...

... fracture gradient slurry Drilling cement job cement slurry expansion machine learning HPHT Upstream Oil & Gas compatibility test result requirement ht condition sensitivity test drilling fluid selection and formulation drilling fluid property society of petroleum engineers annular...

... for predictors trained on data at 0.5ft depth spacing rather than at 1.0 ft depth spacing. Artificial Intelligence oil field well logging resistivity index NPHI determination machine learning neural network predictor prediction entire cored interval log analysis Upstream Oil & Gas true...

... pair of the predictors by using the smoothed terms. All the multivariate statistics analyses of Lithofacies classification and permeability modelling with results visualizations were done through R, the most powerful open-source statistical computing languages. Artificial Intelligence machine...

... correlation machine learning Upstream Oil & Gas simple ann algorithm resilient backpropagation society of petroleum engineers application configuration dataset backpropagation net error qualitative parameter accuracy fluid property neuron reservoir target net error Introduction...

... analysis pressure transient testing correct model Artificial Intelligence node machine learning Upstream Oil & Gas training data neural network training space model identification reservoir model identification reservoir model society of petroleum engineers boundary condition artificial...

.... The first is Teal South in the Gulf of Mexico and the second is Scapa in a North Sea. machine learning history matching mcmc application estimation Artificial Intelligence Upstream Oil & Gas multilevel markov chain monte carlo standard mcmc Teal South reservoir simulation approximation...

..., Formation fluid flow properties and the actual field and well set up, thus providing an advanced EOR Screening. machine learning enhanced recovery neural network operational filter artificial neural network Field Implementation training data regularization parameter algorithm EOR technique...

... technique that may be consistently applied in the interpretation of distributed pressure data or that may be used as a starting point for subsequent interpretations. machine learning regression fluid type pressure transient testing qc score information pretest hydraulic unit mobility pressure...

... in the response. The particular case of fall-off or buildup is studied in detail, as the time lag in reservoir response can bring extra information. A field example is included to demonstrate the application of these methods in a field case and their usefulness to a practicing well test engineer. machine...

... Artificial Intelligence relative time lag pressure transient analysis Upstream Oil & Gas Correlation Chart active well pulse testing equation pressure transient testing spe 164597 pressure response amplitude Pulse Test analysis time lag machine learning odd pulse dimensionless...

... porosity well log case study society of petroleum engineers machine learning accuracy algorithm hydraulic unit estimation fuzzy inference system permeability lithofacies svm support vector machine classification neuron Introduction Estimation of permeability in uncored but logged...

... for resource plays. machine learning unconventional resource economics gas price Energy Economics Upstream Oil & Gas appraisal phase complex reservoir relinquishment Artificial Intelligence investment Manufacturing Approach reduction Exploration Phase Egypt operation spe 164690 key...

... flow in porous media Fluid Dynamics interval pressure carbonate zone machine learning Upstream Oil & Gas Reservoir Characterization completion Artificial Intelligence drillstem/well testing spe annual technical conference spe 164676 reservoir productivity modeling productivity...

...-factor can be determined. A new formula of reduced gas compressibility was developed based on the developed Z-factor correlation which in turn can be used to determine the gas compressibility. Modeling & Simulation Compressibility Factor gas viscosity machine learning PVT measurement gas...

... reservoir simulation Reservoir Characterization Drillstem Testing geological modeling risk management risk assessment drillstem/well testing option value valuation porosity model selection algorithm model selection technique model selection experimental variogram NPV distribution machine...

... time). The new material balance was found to give results with close agreement to the compositional simulation model. machine learning Artificial Intelligence Upstream Oil & Gas Modeling & Simulation PVT measurement new equation separation and treating reservoir simulation...

... information porosity input parameter training error data mining Upstream Oil & Gas prediction training error machine learning neural network Cum GOR Oil Recovery error estimate testing error refinement secondary production permeability spe 164761 Table 2 Performance of the models...

... and duration intervals have been also calculated. structural geology reservoir characterization artificial intelligence fluctuation eccentricity sandstone wavelength cyclicity sequence early permian variation time series analysis machine learning upstream oil & gas permian obliquity...

... associated with the geological model. These analyses that require thousands of simulation runs were performed using the SRM in minutes. machine learning modeling & simulation onshore green field reservoir simulation surrogate reservoir model accuracy grid block data mining upstream oil...