Abstract
Lithology identification is vital for reservoir exploration and petroleum engineering. Recently, there has been growing interest in using an intelligent logging approach for lithology classification. Machine learning has emerged as a powerful tool in inferring lithology types with the logging curves. However, well logs are susceptible to logging parameter manual entry, borehole conditions and tool calibrations. Most studies in the field of lithology classification with machine learning approaches have focused only on improving the prediction accuracy of classifiers. Also, a model trained in one location is not reusable in a new location due to different data distributions. In this paper, a unified framework is provided for training a multi-class lithology classification model for a data set with outlier data. In this paper, a coarse-to-fine framework that combines outlier detection, multi-class classification with an extremely randomized tree-based classifier is proposed to solve these issues. An unsupervised learning approach is used to detect the outliers in the data set. Then a coarse-to-fine inference procedure is used to infer the lithology class with an extremely randomized tree classifier. Two real-world data sets of well-logging are used to demonstrate the effectiveness of the proposed framework. Comparisons are conducted with some baseline machine learning classifiers, namely random forest, gradient tree boosting, and xgboosting. Results show that the proposed framework has higher prediction accuracy in sandstones compared with other approaches.
Highlights
The role of lithology identification in mineral exploration and petroleum exploration has received increased attention across several disciplines in recent years
Our work mainly focuses on multi-class classification, which might result in lower prediction accuracy
Sequential ensemble methods generate the prediction model sequentially by refining the weak learners with the ability to improve the prediction accuracy with lower bias and variance
Summary
The role of lithology identification in mineral exploration and petroleum exploration has received increased attention across several disciplines in recent years. The machine learning algorithms, such as support vector machine, neural network, random forest (RF) and gradient tree boosting (GTB), reduce data analysis work for domain experts and improve the lithology classification accuracy. These machine learning-based approaches to lithology identification attempt to train a multi-class classifiers model based on a large amount of labeled well-logging data with logging curves such as natural gamma (GR) and compensated neutron log (CNL). A coarse-to-fine framework that combines outlier detection, multiclassification with an extremely randomized tree-based classifier is proposed to solve these issues. Results show that the proposed framework helps us gain a higher prediction accuracy in classifying lithology classes, especially sandstone classes
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.