Lithology identification is an indispensable part in geological research and petroleum engineering study. In recent years, several mathematical approaches have been used to improve the accuracy of lithology classification. Based on our earlier work that assessed machine learning models on formation lithology classification, we optimize the boosting approaches to improve the classification ability of our boosting models with the data collected from the Daniudi gas field and Hangjinqi gas field. Three boosting models, namely, AdaBoost, Gradient Tree Boosting, and eXtreme Gradient Boosting, are evaluated with 5‐fold cross validation. Regularization is applied to the Gradient Tree Boosting and eXtreme Gradient Boosting to avoid overfitting. After adapting the hyperparameter tuning approach on each boosting model to optimize the parameter set, we use stacking to combine the three optimized models to improve the classification accuracy. Results suggest that the optimized stacked boosting model has better performance concerning the evaluation matrix such as precision, recall, and f1 score compared with the single optimized boosting model. Confusion matrix also shows that the stacked model has better performance in distinguishing sandstone classes.

Lithology identification is critical in the interpretation of well-logging data for petroleum exploration and development. However, the limited availability of labeled well-logging data for machine learning model training can lead to compromised accuracy in lithology classification models. Here, we propose a semi-supervised lithology identification model to overcome this challenge. Our framework consists of Bayesian optimization for tuning ensemble algorithms, including random forest, gradient boosting decision tree, extremely randomized trees, and adaptive boosting, to establish a high-quality baseline model for semi-supervised learning. We also employ a self-training strategy to increase the number of labeled samples in the training set and use the predicted label with the highest confidence as a pseudo-label to reduce the accumulation of deviation caused by incorrect pseudo-labels. Our semi-supervised coarse-to-fine framework improves rock classification accuracy, particularly for sandstone. Testing our model on well-logging data from two real regions, we found that the ExtraRF-based semi-supervised model in the HGF area performs the best, with a maximum classification accuracy of 91.6 $$\%$$% , which is 5 $$\%$$% higher than the original coarse-to-fine model without using Bayesian optimization and pseudo-labeling techniques.