Asset Details
Do you wish to reserve the book?
A Novel Machine Learning Approach for Detecting Outliers, Rebuilding Well Logs, and Enhancing Reservoir Characterization
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
A Novel Machine Learning Approach for Detecting Outliers, Rebuilding Well Logs, and Enhancing Reservoir Characterization
Do you wish to request the book?
A Novel Machine Learning Approach for Detecting Outliers, Rebuilding Well Logs, and Enhancing Reservoir Characterization
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
A Novel Machine Learning Approach for Detecting Outliers, Rebuilding Well Logs, and Enhancing Reservoir Characterization
2023
Overview
Irregular measurements may occur during the drilling process due to unconsolidated formation resulting in poor signal recordings by the logging tool. This affects the quality of data acquisition and the accuracy of elastic logs, such as density and velocity profiles, in reservoir characterization. It is of paramount importance to ensure the stability of the wireline-logging tool and to prevent compromising measurements of the formation's physical properties. While previous literature focused on the application of different machine learning (ML) algorithms for well logging, their application in a particular domain implied a narrow methodological utility for researchers. Therefore, this study combined two superior techniques of ML, supervised and unsupervised, for enhancing the elastic log response to ultimately help us to enhance reservoir characterization and interpretation. First, the density-based spatial clustering of applications with noise (DBSCAN) was used for outlier detection, and then, feature selection was used to identify highly correlated logs, which helped in rebuilding the density log. After successful ranking, the scaled-down features were carried forward to construct a regression model for density logs rebuilding. The comparative results confirmed the high accuracy of porosity estimated from rebuilt density log compared to that of core data. Consequently, it reduces cumbersome human efforts and time.
Publisher
Springer US,Springer Nature B.V
