A Data-Analytics Tutorial: Building Predictive Models for Oil Production in an Unconventional Shale Reservoir

Abstract

Summary Considerable amounts of data are being generated during the development and operation of unconventional reservoirs. Statistical methods that can provide data-driven insights into production performance are gaining in popularity. Unfortunately, the application of advanced statistical algorithms remains somewhat of a mystery to petroleum engineers and geoscientists. The objective of this paper is to provide some clarity to this issue, focusing on how to build robust predictive models and how to develop decision rules that help identify factors separating good wells from poor performers. The data for this study come from wells completed in the Wolfcamp Shale Formation in the Permian Basin. Data categories used in the study included well location and assorted metrics capturing various aspects of well architecture, well completion, stimulation, and production. Predictive models for the production metric of interest are built using simple regression and other advanced methods such as random forests (RFs), support-vector regression (SVR), gradient-boosting machine (GBM), and multidimensional Kriging. The data-fitting process involves splitting the data into a training set and a test set, building a regression model on the training set and validating it with the test set. Repeated application of a “cross-validation” procedure yields valuable information regarding the robustness of each regression-modeling approach. Furthermore, decision rules that can identify extreme behavior in production wells (i.e., top x% of the wells vs. bottom x%, as ranked by the production metric) are generated using the classification and regression-tree algorithm. The resulting decision tree (DT) provides useful insights regarding what variables (or combinations of variables) can drive production performance into such extreme categories. The main contributions of this paper are to provide guidelines on how to build robust predictive models, and to demonstrate the utility of DTs for identifying factors responsible for good vs. poor wells.

Dimensionality reduction for multi-criteria problems: An application to the decommissioning of oil and gas installations

“…In a related work, El-Abbasy et al (2016) make use of regression analysis, artificial neural networks and DT to investigate the causes of pipeline failure. Other works were concerned with predicting oil production (Schuetter et al, 2018;Li and Chan, 2010). The former utilises classification models, such as SVM and Gradient Boosting Machines (GBM), to predict oil potential in unconventional reservoirs.…”

The Production Performance Evaluation of Hydraulically Fractured Wells in the East Sulige Field Using Machine Learning

“…We must first decide on which machine learning algorithm works best to predict the well productivity since there are so many machine learning algorithm available such as ordinary least squares regression, support vector machine, neural network, and tree-based methods including decision tree, random forest, gradient boosting model. A comparison of their relative strengths and weakness was listed by Schuetter [5]. The optimal algorithm suitable for the data set is determined by trying the multiple algorithms through trial and error.…”

Machine learning on field data for hydraulic fracturing design optimization

“…Source Cumulative oil production 6/18 month just after the job [24] 12 months cumulative oil production [25] Average monthly oil production after the job [19] NPV [26] Comparison to modelling [28] Delta of averaged Q oil [29] Pikes in liquid production for 1, 3 and 12 months [30] Break even point (job cost equal to total revenue after the job) [32] • In [26], a procedure was presented to optimize the fracture treatment parameters such as fracture length, volume of proppant and fluids, pump rates, etc. Cost sensitivity study upon well and fracture parameters vs NPV as a maximization criteria is used.…”