A Real‐time Lithological Identification Method based on SMOTE‐Tomek and ICSA Optimization

In petroleum engineering, real‐time lithology identification is very important for reservoir evaluation, drilling decisions and petroleum geological exploration. A lithology identification method while drilling based on machine learning and mud logging data is studied in this paper. This method can...

Full description

Saved in:
Bibliographic Details
Published inActa geologica Sinica (Beijing) Vol. 98; no. 2; pp. 518 - 530
Main Authors DENG, Song, PAN, Haoyu, LI, Chaowei, YAN, Xiaopeng, WANG, Jiangshuai, SHI, Lin, PEI, Chunyu, CAI, Meng
Format Journal Article
LanguageEnglish
Published Richmond Wiley Subscription Services, Inc 01.04.2024
EditionEnglish ed.
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:In petroleum engineering, real‐time lithology identification is very important for reservoir evaluation, drilling decisions and petroleum geological exploration. A lithology identification method while drilling based on machine learning and mud logging data is studied in this paper. This method can effectively utilize downhole parameters collected in realtime during drilling, to identify lithology in real‐time and provide a reference for optimization of drilling parameters. Given the imbalance of lithology samples, the synthetic minority over‐sampling technique (SMOTE) and Tomek link were used to balance the sample number of five lithologies. Meanwhile, this paper introduces Tent map, random opposition‐based learning and dynamic perceived probability to the original crow search algorithm (CSA), and establishes an improved crow search algorithm (ICSA). In this paper, ICSA is used to optimize the hyperparameter combination of random forest (RF), extremely random trees (ET), extreme gradient boosting (XGB), and light gradient boosting machine (LGBM) models. In addition, this study combines the recognition advantages of the four models. The accuracy of lithology identification by the weighted average probability model reaches 0.877. The study of this paper realizes high‐precision real‐time lithology identification method, which can provide lithology reference for the drilling process.
Bibliography:dengsong@cczu.edu.cn
DENG Song, professor, and master advisor at Changzhou University. Ph.D., graduated from China University of Petroleum (Beijing). He is committed to the scientific research of oil and gas artificial intelligence, exploration and development of new energy and new materials, carbon capture, utilization and storage (CCUS), offshore oil and gas engineering, etc., and published 15 SCI/EI and other high‐level papers, 6 invention patents authorized by the first inventor. E‐mail
.
About the first and corresponding author
ISSN:1000-9515
1755-6724
DOI:10.1111/1755-6724.15144