... gravity drainage enhanced recovery regression sagd concentration prediction data-driven method operator machine learning recommendation improved operational carbon footprint reduction algorithm consideration thermal method blockage threshold chemical treatment candidate selection field...

... i + 2.18 l o g r 10 where k : dry gas permeability (mD), Phi : Porosity (%), Linear regression is one of the straightforward statistical tools which is used to predict a response variable (y) starting from explanatory variables (x); this approach could...

... Quality control for the data set was individually performed for the trend model and regression model. First, the data set was screened on an operator basis. Presumably, operators with more wells in the area maintain consistency in recording and quality control of the data, which are believed...

... properties and density changes by the addition of various levels of LGS and HGS. Using this dataset, multi-linear, Ridge, Lasso, K-nearest neighbors (KNN), and Random Forest (RF) regression models were trained and tested to predict LGS and HGS content of drilling fluids. A key advantage of this machine...

... Multivariable regression innately accounts for all manner of microscopic and macroscopic interactions as a function of the governing volumetric nature of the dielectric probe method. Adaptation of the model stems from the isolation of individual parameters contained in the regression where...

..., i.e. what is or is not an outlier; only that a regression of a known model to the data must be statistically robust (not influenced by outliers). We evaluate the method by application using publicly available data to every horizontal well in the Midland and Delaware basins put on production since...

... for single-well pressure behavior. Tian and Horne (2019) proved that the learning quality of linear regression is equivalent to the convolution kernel method with lower computational cost and dubbed it feature-based machine learning that included linear regression, ridge regression, and kernel ridge...

... (EURs) for new wells. This methodology utilizes regression to correlate easy to obtain, early life indicators of well performance to 2P EURs, which have been estimated from more detailed interpretations. Multiple methodologies are presented for estimating 1P and 3P EURs. asset and portfolio...

..., the vertical extension of fault leakage to shallower formations is evaluated. Fluid Dynamics fault leakage fluid flow regression diffusivity equation analytical model Zeidouni derivative Upstream Oil & Gas injection zone shallower formation storage flow in porous media equation pressure...

... regression (ULR) and multiple linear regression (MLR), and decision tree analysis (DTA) (classification) and neural network analysis (NNA). The workflow ( Fig. 1 ) makes automatic prediction possible. DTA enables predicting the probability of tight formation, and ULR enables estimating the relationship...

... Abstract Choosing the most profitable wells for steam jobs is of high value given the cost and resources required for the procedure. To find the best candidates, we develop a system with two parts: i) An autoencoder to reduce the dimensionality of input data, ii) A kernel regression to predict...

... properties, mud hydraulics, borehole deviation as well as the size/type of bit. Traditional regression analysis models have limitations and have limited accuracy while attempting to describe the dependence of one observed quantity on another observed quantity. On the other hand, the artificial intelligence...

... is developed and, the early and late transient solutions are analyzed; A robust inversion technique for parameter estimation is presented using exponentially decaying late transient data; Most importantly, the inversion technique is based on a linear regression and numerical integration rather than a non...

... regression for pressure deconvolution. Kernel ridge regression was shown to speed up the computation and recover the early transient behaviors, while maintaining the advantages of the convolution kernel method described by Liu and Horne (2013a , 2013b ), which was effective but expensive computationally...

... the geothermal due to Joule-Thomson expansion of the reservoir oil. Production is single phase oil from a high pressure oil reservoir. Nonlinear regression was used to automatically adjust the layer permeability and skin values until the observation temperature traces from both rates were matched. History...

... patterns. Using a commercial reservoir properties database, we created and tested four data analytic models to predict ultimate oil and gas recovery efficiencies, using the following methods borrowed from data analytics: linear regression, linear regression with feature selection, Bayesian network...

... . The subsequent regression process searches for an optimum set of T C , P C , and ω in physically justified directions. The regression algorithm developed does not require user's experience of thermodynamic modeling for robust convergence. The NM also satisfies Pitzer's definition of ω for each component. The NM...

... estimation regression seismic inversion geophysics perpendicular organic shale Anisotropy correction anisotropy Introduction Most rocks exhibit velocity anisotropy at all scales. This means that the compressional and shear velocities vary with the direction of wave propagation. The preferred...

... the problem we may need to reduce the number of features, using feature selection techniques or dimension reduction techniques, like principal component analysis or nonlinear techniques. The data would then be ready for pattern recognition techniques like clustering, classification and regression...

... and the closest points on the pressure transient to the data points. These methods will be discussed in detail in the subsequent sections. Summed Distance Regression (SDR) The first TLS method we analyzed sums the squares of errors in time and pressure in a single objective function. In a traditional least...