... machine learning and deep learning algorithms to predict missing log values from other commonly available logs, such as resistivity, density, gamma ray, neutron porosity, photoelectric factor, etc. Linear regression, Principal Component Regression (PCR), Partial Least Squares Regression (PLSR), random...

... to propagate all input uncertainties for different rock types, mud types, and mud slowness profiles. The mud slowness uncertainties are estimated by applying different regressions of inverted mud slownesses and comparing these regressions to known values. A Monte Carlo approach is then used to propagate all...

... artificial intelligence estimation exploration geophysicist upstream oil & gas machine learning regression reservoir characterization application applied geoscience society toc assessment linear regression algorithm prediction evaluation international american association...

... acquisition society hydrophone upstream oil & gas regression international american association noise energy 10 Characterization and simulation of transverse noise waves of a multi-sensor solid streamer Viktor Smirnov* (Sercel / Univ. Grenoble-Alpes, GIPSA-Lab), A. Sourice (Sercel), J. Ribette...

... refraction exploration geophysicist cable interrogator upstream oil & gas international american association accelerometer society reservoir characterization trench helically energy 10 regression dataset applied geoscience co-located dataset estimation fiber cable...

... and sedimentary facies. The training with a small well data set (1– 10 wells) leads to low and unstable test scores ( R 2 = 0.2– 0.7). The R 2 score increases and stabilizes with more (as many as 1000) training wells ( R 2 = 0.7– 0.9). Sparse well-supported models can outperform linear regression and model...

... computationally as the number of features grows. Glubokovskikh et al. (2020) proposed a 1 PDC 6-blade Push-the-bit workflow for sampling the importance of the predictive features using a greedy algorithm an ensemble of 2 PDC 6-blade Push-the-bit stagewise quadratic regressions. This algorithm gradually...

... sufficient information to distinguish the effects associated information to distinguish the signal from crushing rock and with the drillstring noise and rock properties. To this end, drillstring-related noise. We believe that the physics may be we modified the forward stagewise regression to provide a too...

... ABSTRACT We investigate potential applications of two machine learning methods, random forest regression and support vector regression, in aeromagnetic data interpolation. By developing relevant predictors, and training these two methods on synthetic aeromagnetic data, we are able...

.... In this paper we lay a series of supervised regression methods that proved highly predictive when compared to existing methods of estimating undrilled well production. We conducted an extensive machine learning modeling exercise using data from an active Jonah Energy (Jonah) gas field in Sublette County...

... detection kit chamber reservoir characterization regression Allen , R. V. , 1978 , Automatic earthquake recognition and timing from single traces : Bulletin of the Seismological Society of America , 68 , 1521 – 1532 . Cortes , C. , and V. Vapnik , 1995...

... from well information. The combination of 7 seismic attributes including P wave and density, derived from inversion was used in the step-wise regression. The network was trained with shale content data available at well locations to generate a shale volume. 3D seismic data was used to propagate...

... inversion (layer thicknesses and resistivities are inversion parameters) for the final resistivity model. Both steps use rescaled Ridge Trace least square regressions. The computer program for this method determines other the input parameters from the data file. The method utilizes an integrated program...

... already been estimated by seismic inversion. Our method is based on the probabilistic nearest neighbor (k-nn) method, but also incorporates feature selection and nonlinear regression. To improve upon the standard k-nn method, we incorporate a regression approach based on the Bayesian MARS model...

... Agterberg , F. P. , G. F. Bonham-Carter , Q. Cheng , and D. F. Wright , 1993 , Weights of evidence modeling and weighted logistic regression for mineral potential mapping , in J. C. Davis , and U. C. Herzfeld , eds. , Computers in Geology, 25...

... artificial intelligence regression annual meeting annual meeting depth iteration count 1 inversion geophysics reservoir characterization axis regularization reference list annual international meeting velocity-stack inversion moveout parameter application Bube , K. , and R...

... Type: ORAL regression multivariate linear regression annual meeting carbonate rock classification fluid dynamics upstream oil & gas flow in porous media seg seg international exposition gas permeability permeability dependence p-wave velocity dolostone linear regression machine...

... are extracted from seismic data along wellbores in the depth domain. Seismic estimates of mechanical parameters are derived from seismic inversion and AVAz analysis. We show the results of several correlation techniques including multi-linear regression, neural networks, and alternating conditional expectation...

... modulus of a rock from mineral moduli and porosity. Most of them are empirical, derived from best fittings regressions of well logging or core measurements. In this work, we analyzed datasets containing the porosity, mineral moduli and elastic velocities, obtained in grainstone core plugs at different...

... vrm vint seismic inversion seismic horizon regression reservoir characterization initial model instantaneous phase annual international meeting upstream oil & gas skeleton relative inversion seg interval velocity david monk application seismic skeleton inversion skeleton...