A novel approach to the automatic classification of wireline log-predicted sedimentary microfacies based on object detection.

The wireline log prediction of sedimentary microfacies plays a significant role in sedimentary study. It is mainly achieved through the manual interpretation of wireline logs according to the differences of sedimentary microfacies in wireline log shapes. Influenced by interpreters' expertise and proficiency in manual interpretation, the classification results maybe subjective and uncertain. Moreover, the task is labor intensive. Developing an automatic method based on wireline logs to accurately classify sedimentary microfacies is thus, a worthy consideration. The proposed automatic classification of sedimentary microfacies in this study can be implemented in terms of object detection, which involves aspects of machine learning and computer vision. In the stage of machine learning, we manually extract the features that can represent the different well log shapes of sedimentary microfacies. To solve the problem of imbalanced training samples, we use the oversampling technique to propagate the training classes with few samples. In addition, based on the augmented samples, we systematically conduct cross-validation and hyperparameter optimization on a series of machine learning algorithms with different mechanisms. The oversampling algorithm and machine learning model with the best performance can then be selected. In the stage of computer vision, we design an object detection strategy to detect the classes and locations of sedimentary microfacies by integrating the trained classifier. The practical application of the proposed method to the clastic strata of the Ordos basin proves its efficiency and consistency in automatically classifying sedimentary microfacies. [ABSTRACT FROM AUTHOR]