Abstract
This study presents an approach based on machine learning to predict the lithology at the bit while drilling. This is necessary for (near) real-time adjustments of well path while providing reservoir characterization (reservoir rock, non-reservoir rock and tight rocks). The approach is based on an ensemble of decision trees and gradient boosting. Work on this project included analysis and preprocessing of the data, selection of features for training, creation of additional features to improve the quality of the model, comparison of machine learning algorithms to identify the most effective within the task, optimization of the hyperparameters. After that, the final model is built on a training dataset with desired outputs obtained from LWD formation evaluation and the quality of the algorithm is evaluated on a test dataset with the selected metrics.
The computer program developed on the proposed approach receives drilling data as input and provides a reservoir characterization. High quality of the model is necessary for successful geosteering of horizontal wells due to the rapid detection of lithology changes in the reservoir and increasing the efficiency of well drilling by minimizing penetration through the non-reservoir rocks, which can further increase oil production. The proposed approach provides an accuracy of 80-90% for a number of oil fields.
