... reservoir characterization hydrocarbon productivity facies thickness bone spring formation structural geology geointegra consulting rock type montgomery fairfield geotechnology geological subdiscipline control regression non-linear regression saturation new mexico URTeC: 3862919 Predicting...

... learning gradient seg unconventional resource technology conference modeling regression artificial intelligence production control technology conference algorithm scenario leak-off scenario URTeC: 3870194 Modeling of Fiber-Optic Strain Response when Pumping Stops to Verify Potential...

... of porosity and permeability. Different machine learning algorithms have been developed including Linear Regression (LR), Artificial Neural Network (ANN), Random Forest Regressor (RFR), Extreme Gradient Boosting (XGBoost), Adaptive Booster Regressor (AdaBoost), and Support Vector Regression (SVR), to predict...

... design a cross-validation technique that we use to test multiple configurations of ML architectures using linear regression, support-vector regression (SVR), and random forest (RF). The results show promising potential for ML methods to assist reservoir engineers and increase the confidence in the BHFP...

.... The training set was fed into the ANN model and the results were compared with the results obtained from other inherently spatial methods such as universal kriging, geographically weighted regression (GWR), and generalized additive model (GAM). Finally, the EUR of the new wells were compared to the original...

... drilling reserves evaluation urtec 3269 drillstem/well testing unconventional resource economics university of tulsa regression contribution artificial intelligence geometry exponential decline decline curve analysis interpretation shale gas noise reservoir simulation upstream oil & gas...

... overhead. The compressional and shear velocities (Vp and Vs respectively) can be used to calculate Young s modulus, Poisson s ratio and other mechanical properties. In the field, sonic logs are not commonly acquired and operators often resort to regression to predict synthetic sonic logs. We have compared...

...-out-cross-validation by training on 45 of the wells and blind testing on the remaining five. Mean Absolute Percentage Error (MAPE) was used to compare the models because it allows a percentage estimate of ROP prediction accuracy. The winning model was multivariate adaptive spline regression because...

... Upstream Oil & Gas machine learning Proc training dataset classification traditional feature regression prediction Artificial Intelligence spe annual technical conference algorithm node pore circularity Exhibition mechanical property artificial neural network microstructure...

... the basin and interpolated to provide a 3D volume of estimated TOC. The calculated curves and 3D model were QC'd visually and semi-statistically and found to be a reasonable match to the core data, given the methodology well logging log analysis regression URTeC core measurement machine learning...

... Artificial Intelligence cumulative production information neural network ensemble model predictor Upstream Oil & Gas ensemble strategy training data machine learning regression prediction unconventional reservoir society of petroleum engineers model prediction variability...

... regions that could be troublesome. Calibrated models have been successfully developed in the Permian and Williston Basins. In this demonstration of the concept, we will show a prediction of frac gradient (FG) in the Williston Basin. geologic modeling Reservoir Characterization regression...

... of clay. The data was randomly partitioned into a 70:30 split for training and validation data set respectively. Model competition among a suite of machine learning algorithms such as Linear Regression, Artificial Neural Networks (ANNs), Decision Trees, Gradient Boosting and Random Forest was used...

... Intelligence strength regression ROP prediction motahhari Upstream Oil & Gas hybrid model accuracy ROP model deterministic model feature importance equation Bingham random forest inference algorithm penetration prediction data-driven model Drilling URTeC: 2896522 Rate of penetration...

... machine learning Artificial Intelligence dgn Upstream Oil & Gas regression reservoir simulation conditional realization vector history-matched model realization History flow response optimization problem gradient sensitivity matrix objective function production data...

... Artificial Intelligence Drillstem Testing Modeling & Simulation complex reservoir drillstem/well testing Fluid Dynamics flow in porous media oil shale regression initial slope Bakken production data MSTB interference forecasting production prediction watercut Bakken well...

... or "learner" using a training data set to predict the value of an outcome based on a number of inputs, is generally referred to as "supervised learning" [4]. Such problems can be further subdivided into: regression problems, where the response variable is continuous, or classification problems, where...

... Installation and Operations regression traditional method EUR estimation Completion Efficiency operational problem Reservoir Surveillance Upstream Oil & Gas quantile regression method individual well aggregate quantile regression Efficiency Engineer qr method Summary This paper...

... framework and measure rock fabric variability. These approaches can potentially identify crucial reservoir properties. Ti, Zr, K, and Al, show a general transgression in the lower 260ft with superimposed higher-frequency transgressions and regressions. This portion of the unit also show consistently high...

... machine learning complex reservoir lateral length well performance Upstream Oil & Gas information shale gas regression Artificial Intelligence inflow performance Well Productivity coefficient placement equation correlation matrix multivariate analysis Pump Rate multivariate...