Lithology identification of igneous rocks based on XGboost and conventional logging curves, a case study of the eastern depression of Liaohe Basin

• Published in: Journal of applied geophysics Vol. 195; p. 104480
• Main Authors: Ruiyi, HAN, Zhuwen, WANG, Wenhua, WANG, Fanghui, XU, Xinghua, QI, Yitong, CUI
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2021
• Subjects: Igneous rock; Lithology classification; XGboost; XGboost; Lithology classification; Igneous rock
• ISSN: 0926-9851; 1879-1859
• DOI: 10.1016/j.jappgeo.2021.104480

The lithofacies and lithology of igneous rocks in the eastern depression of Liaohe basin are complex, with the characteristics of heterogeneity and anisotropy, which puzzles logging interpretation. To identify their lithology, 2663 complete and continuous logging data of cuttings and 5 conventional logging curves (SP, AC, DEN, GR and CNL) from 7 wells in the eastern depression of Liaohe basin are selected as the training set based on the comprehensive thin section data and logging data of igneous rocks,. Three lithology identification schemes based on XGboost are established to classify lithology. By comparing the classification results with lithologic profile and thin section data, a practical scheme for lithologic classification of igneous rocks in the eastern depression of Liaohe basin is obtained, and the classification accuracy is 98.99%. •Igneous rock classification scheme based on xgboost has an accuracy of 98.99%.•Data preprocessing to improve classification efficiency•Classification of anisotropic igneous rocks based on conventional logging curves