LAUSR

Lithology identification based on conventional well-logging data is of great importance for geologic features characterization and reservoir quality evaluation in the exploration and production development of petroleum reservoirs. However, there are some limitations in the traditional lithology identification process: (1) It is very time consuming to build a model so that it cannot realize real-time lithology identification during well drilling, (2) it must be modeled by experienced geologists, which consumes a lot of manpower and material resources, and (3) the imbalance of labeled data in well-log data may reduce the classification performance of the model. We have developed a gradient boosting decision tree (GBDT) algorithm combining synthetic minority oversampling technique (SMOTE) to realize fast and automatic lithology identification. First, the raw well-log data are normalized by maximum and minimum normalization algorithm. Then, SMOTE is adopted to balance the number of samples in each class in training process. Next, a lithology identification model is built by GBDT to fit the preprocessed training data set. Finally, the built model is verified with the testing data set. The experimental results indicate that the proposed approach improves the lithology identification performance compared with other machine-learning approaches.