Correlating geologic and seismic data with unconventional resource production curves using machine learning

Predicting well production in unconventional oil and gas settings is challenging due to the combined influence of engineering, geologic, and geophysical inputs on well productivity. We have developed a machine-learning workflow that incorporates geophysical and geologic data, as well as engineering completion parameters, into a model for predicting well production. The study area is in southwest Texas in the lower Eagle Ford Group. We make use of a time-series method known as functional principal component analysis to summarize the well-production time series. Next, we use random forests, a machine-learning regression technique, in combination with our summarized well data to predict the full time series of well production. The inputs to this model are geologic, geophysical, and engineering data. We are then able to predict the well-production time series, with 65%–76% accuracy. This method incorporates disparate data types into a robust, predictive model that predicts well production in unconventional resources.

[1]  Spencer Graves,et al.  Functional Data Analysis with R and MATLAB , 2009 .

[2]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[3]  Tor Arne Johansen,et al.  Incorporating 4D Seismic Data in Reservoir Simulation Models Using Ensemble Kalman Filter , 2007 .

[4]  Kurt J. Marfurt,et al.  3D volumetric multispectral estimates of reflector curvature and rotation , 2006 .

[5]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[6]  James O. Ramsay,et al.  Functional Data Analysis , 2005 .

[7]  Ursula Iturrarán-Viveros,et al.  Smooth regression to estimate effective porosity using seismic attributes , 2012 .

[8]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2001, Springer Series in Statistics.

[9]  Samuel D. Fluckiger,et al.  New methodology merging seismic, geologic, and engineering data to predict completion performance , 2017 .

[10]  Mohammad Ali Riahi,et al.  Estimation of Reservoir Porosity and Water Saturation Based on Seismic Attributes Using Support Vector Regression Approach , 2014 .

[11]  I. Jolliffe.  Principal Component Analysis , 2002 .

[12]  A. Roberts.  Curvature attributes and their application to 3D interpreted horizons , 2001 .

[13]  T. Mukerji,et al.  Improving curvature analyses of deformed horizons using scale-dependent filtering techniques , 2003 .

[14]  Kan Wu,et al.  Development of a Powerful Data-Analysis Tool Using Nonparametric Smoothing Models To Identify Drillsites in Tight Shale Reservoirs With High Economic Potential , 2017 .

[15]  Julia F. W. Gale,et al.  Natural fractures in the Barnett Shale and their importance for hydraulic fracture treatments , 2007 .

[16]  Tor Arne Johansen,et al.  Incorporating 4D Seismic Data in Reservoir Simulation Models Using Ensemble Kalman Filter , 2005 .

[17]  Jef Caers,et al.  Functional Approach to Data Mining, Forecasting, and Uncertainty Quantification in Unconventional Reservoirs , 2015 .

[18]  J. Soldo,et al.  Curvature attributes and seismic interpretation Case studies from Argentina basins , 2003 .

[19]  T. Mukerji,et al.  Quantitative Seismic Interpretation: Applying Rock Physics Tools to Reduce Interpretation Risk , 2005 .