... testing production monitoring stabilization coefficient enhance gas well testing exploring petroleum engineer society dataset deliverability upstream oil & gas artificial intelligence machine learning application regression metric Introduction The history of gas well...

... Regression as introduced by ( McCain, 1998 ) using alternating conditional expectations (ACE) for selecting multiple regression transformations 2), Genetic programing and heuristic modeling using Symbolic Regression (SR) and cross validation for model automatic tuning 3) Machine learning predictive model...

... in this paper. The implemented solution replicates performance of unconventional wells using transient models. Input parameters for all models honour a given range of realistic operational conditions and are automatically regressed to match the historical performance. At a specified interval, historical...

... Multiple stage regression modelling added predictive power to conventional single pass multivariate regression. In this process, a multivariate regression model was created using an early-time portion of the training dataset. The prediction results of this first regression model were then added...

... structural geology reservoir characterization flow in porous media artificial intelligence regression facies mungaroo formation chevron wireline log permeability reservoir sand workflow woodside petroleum predict permeability australia fluid dynamics grain size ellipse carnarvon basin well...

... architecture regression Introduction CO 2 injection is an EOR project with the most amount of interest. This has been the trend since 2002. Currently, CO 2 and thermal are the two EOR methods most frequently implemented around the world ( Surguchev et al. 2005 ) and contribute to most significant...

... in modeling. The proposed model predicts the bubble point pressure ( P b ) and the oil formation volume factor at bubble point pressure ( B ob ) as a function of oil and gas specific gravity, solution gas-oil ratio, and reservoir temperature by a boosted decision tree regression (BDTR) predictive modeling...

... class membership (e.g. Decision Tress, Neural network. K-means clustering, Self-Organizing Maps) Regression models that predict a number (Linear, Logistic, Random Forest, Gradient Boosting Machine, Support Vector Machine) Past Application in Oil and Gas Challenges Artificial neural networks...

... of permeability values. In a homogenous sand unit, the conventional model can be used up to a certain degree of accuracy. machine learning pressure transient testing petrophysical facies model pressure transient analysis flow in porous media regression Reservoir Characterization Upstream Oil...

... NZBP candidates empirically and statistically. After generating a screening process, the next step is to build reliable forecasting methods for future NZBP job. Therefore, we utilize the equation resulted from previous multi-variable linear regression and 2 nd degree polynomial regression to estimate...

... for PL analysis in a 3-phase well. The results of the statistical analysis indicate that gas rate, oil rate, and water cut are critical for flow correlation selection. production control production logging gas liquid slippage reservoir surveillance regression machine learning artificial...

... is achieved. This happens where rock skeleton is very stiff. Where rock framework is loose, estimated AI is strongly affected by the presence of hydrocarbons. In this study, important observation is at the time one applies the linear regression to inversion data. The resulting porosity volume is severely...

... as a nonlinear regression method to develop transformation between the selected well logs and core measurements. The technique is demonstrated with an application to the well data in offshore Korea. The results show that the technique can make more accurate and reliable reservoir properties estimation compared...

.... The benefits of using cutting samples are; measurement of vector permeability, cutting faces are not damaged hence, more realistic measurement, and this measurement is made instantly in the field. permeability measurement permeability regression fluid dynamics permeameter flow in porous media...

... point pwf regression two-rate test straight line drillstem/well testing semi-log plot coefficient flow rate log-log plot storage capacity ratio cartesian plot reservoir upstream oil & gas drillstem testing skin factor interporosity flow coefficient fractured reservoir equation...

..., initial wellbore pressure, etc. Perform Regression to Optimize Permeabilities and Other Key Parameters such as Skin Sensitive Analysis (if necessary) to define confidence limits for the estimated parameters and to indicate the degree of correlation between them [ 1 ][ 9 ] This approach...

... Valley are adapted to operations in Sumatra. well logging temperature log multiple regression oil saturation log analysis pulsed neutron capture capture cross section kern river field saturation calculation equation saturation kern river duri steam saturation california upstream oil...

... and the same physical properties of each pseudo-component while the mole fractions of pseudo-components reflect the overall distribution of C 7+ mixtures. In addition, a regression technique has been developed to fit the PVT data and phase behavior for single or multiple samples of reservoir fluids...

... of the geo-regression. In the geo-regression, the - the reservoir Z600 uniquely composed of sandstone and clays The Z600 reservoir can be divided into 4 sub-layers separated by small shally formations (lm). We call these sub layers A, B, C and D. The porosity saturation analysis compared with production well...

... production logging water regression INTRODUCTION The oil industry requires a multiphase flow meter to determine the flow rates of oil, water and gas in pipelines from oil wells. The MFM must be compact and mounted directly onto each well pipeline. It must continuously determine the flow rates to 5...