International Journal on Advanced Science, Engineering and Information Technology, Vol. 11 (2021) No. 2, pages: 542-548, DOI:10.18517/ijaseit.11.2.11764

Lithofacies Classification Using Supervised and Semi-Supervised Machine Learning Approach

Lilik T. Hardanto, Lili Ayu Wulandhari


The machine learning approach can help Geoscientists do their work in well log analysis to developing the oil and gas field. Prediction categorical or numerical response variable using a set of predictor variables supervises and semi-supervises learning is an important goal of the machine learning approach in classifying lithofacies using well log data. Semi-supervised classification offers the possibility of exploring the structure of the data without entirely external knowledge or guidance in the form of target or class information, and semi-supervised is very rarely research in the field of lithofacies classification.  Well log data in gamma-ray, resistivity, neutrality, and density logs are collected and selected for data processing and transformation. The use of machine learning algorithms such as Naïve Bayes, SVM, and Decision Tree is to find the log pattern or pattern classifications of lithofacies in supervised and semi-supervised to create a model with conditions requiring the change of data and the corresponding requirements. All supervised machine learning algorithms have the best accuracy because algorithms provide useful predictive in classifications based on the target but not if there are no targets given or semi-supervised. This paper compares some of the famous classification algorithms of machine learning, such as Decision tree, SVM, and Naïve Bayes, on classifying lithofacies with supervised and semi-supervised learning. This research found that the semi-supervised learning of Naïve Bayes has performed well in classified lithofacies. In contrast, in supervised learning, Decision Tree and SVM are superior in accuracy and visualization approach based on expert’s interpretation.


Machine learning; decision tree; SVM; naïve bayes; lithofacies; supervised; semi-supervise learning.

Viewed: 252 times (since abstract online)

cite this paper     download