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.
Proppant diagenesis, as a topic of discussion in the industry, tends to generate negative reactions. Potential solutions, such as un-reactive coatings, cost money. Early research was done at substantially higher temperatures than many considered realistic, but was an attempt to shorten test times in order to begin to understand the phenomenon. Regardless of objections and negative reactions, the subject needs to be understood, because long term well performance implications may be significant.The purpose of this paper is to present a progress report on the results of long-term proppant diagenesis tests using coated and uncoated proppants, with and without shale reservoir rock present in the test cell, and in the presence of fluids of varying composition. Test philosophy and methods are described. Test results are documented using electron micrographs as well as chemical analysis and particle strength tests. Specific changes in fluid chemistry that result from contact with proppant and shale at reservoir temperature will also be a focus of the paper.
This paper documents a data-mining study of well, hydraulic fracture treatment, and production parameters for horizontal wells in the north Texas Barnett Shale play. In this study, the authors have analyzed well and production data from more than 13,400 producing Barnett wells. A subsample of over 3,300 horizontal wells was characterized with respect to detailed well architecture data such as drift direction and angle, lateral length, perforations, etc. The study uses Geographical Information System pattern-recognition techniques in conjunction with more traditional statistical techniques to interpret hidden trends in otherwise scattered data sets. This work provides a case study in the practical use of data-mining techniques to address questions of best practices in Shale Gas reservoirs. It is made possible because the availability and quality of public domain well and production data has increased significantly in the past few years. Simple cross plotting of production data against well and treatment variables normally leads to broad scattering of results. This study takes advantage of the largest, richest well and production data set available from the gas shales and identifies key lessons-learned. Relevant trends, such as the impact of toe up versus flat versus toe down, horizontal well length, and drift angle variability on gas production rate are presented. This work is significant in that it shows that the application of practical data-mining methods to a large Shale Gas data set can result in learning key lessons that may not be apparent when working with small data sets. This work is also significant in the use of merged reservoir quality proxies, well architecture data, completion data, and stimulation data, against which production results are placed in geographical perspective for improved interpretation.
Data mining for production optimization in unconventional reservoirs brings together data from multiple sources with varying levels of aggregation, detail, and quality. Tens of variables are typically included in data sets to be analyzed. There are many statistical and machine learning techniques that can be used to analyze data and summarize the results. These methods were developed to work extremely well in certain scenarios but can be terrible choices in others. The analyst may or may not be trained and experienced in using those methods. The question for both the analyst and the consumer of data mining analyses is, "What difference does the method make in the final interpreted result of an analysis?"The objective of this study was to compare and review the relative utility of several univariate and multivariate statistical and machine learning methods in predicting the production quality of Permian Basin Wolfcamp Shale wells. The data set for the study was restricted to wells completed in and producing from the Wolfcamp. Data categories used in the study included the well location and assorted metrics capturing various aspects of the well architecture, well completion, stimulation, and production. All of this information was publicly available.Data variables were scrutinized and corrected for inconsistent units and were sanity checked for out-of-bounds and other "bad data" problems. After the quality control effort was completed, the test data set was distributed among the statistical team for application of an agreed upon set of statistical and machine learning methods. Methods included standard univariate and multivariate linear regression as well as advanced machine learning techniques such as Support Vector Machine, Random Forests, and Boosted Regression Trees.The strengths, limitations, implementation, and study results of each of the methods tested are discussed and compared to those of the other methods. Consistent with other data mining studies, univariate linear methods are shown to be much less robust than multivariate non-linear methods, which tend to produce more reliable results. The practical importance is that when tens to hundreds of millions of dollars are at stake in the development of shale reservoirs, operators should have the confidence that their decisions are statistically sound. The work presented here shows that methods do matter, and useful insights can be derived regarding complex geosystem behavior by geoscientists, engineers, and statisticians working together.
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: (a) how to build robust predictive models, and (b) 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 Random Forests, Support Vector Regression, Gradient Boosting Machine 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 versus bottom x% as ranked by the production metric) are generated using the classification and regression tree algorithm. The resulting decision tree provides useful insights as to 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 decision trees for identifying factors responsible for good versus poor wells.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.