Towards Optimization of Boosting Models for Formation Lithology Identification
Joint Authors
Xie, Yunxin
Zhu, Chenyang
Lu, Yue
Zhu, Zhengwei
Source
Mathematical Problems in Engineering
Issue
Vol. 2019, Issue 2019 (31 Dec. 2019), pp.1-13, 13 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2019-08-14
Country of Publication
Egypt
No. of Pages
13
Main Subjects
Abstract EN
Lithology identification is an indispensable part in geological research and petroleum engineering study.
In recent years, several mathematical approaches have been used to improve the accuracy of lithology classification.
Based on our earlier work that assessed machine learning models on formation lithology classification, we optimize the boosting approaches to improve the classification ability of our boosting models with the data collected from the Daniudi gas field and Hangjinqi gas field.
Three boosting models, namely, AdaBoost, Gradient Tree Boosting, and eXtreme Gradient Boosting, are evaluated with 5-fold cross validation.
Regularization is applied to the Gradient Tree Boosting and eXtreme Gradient Boosting to avoid overfitting.
After adapting the hyperparameter tuning approach on each boosting model to optimize the parameter set, we use stacking to combine the three optimized models to improve the classification accuracy.
Results suggest that the optimized stacked boosting model has better performance concerning the evaluation matrix such as precision, recall, and f1 score compared with the single optimized boosting model.
Confusion matrix also shows that the stacked model has better performance in distinguishing sandstone classes.
American Psychological Association (APA)
Xie, Yunxin& Zhu, Chenyang& Lu, Yue& Zhu, Zhengwei. 2019. Towards Optimization of Boosting Models for Formation Lithology Identification. Mathematical Problems in Engineering،Vol. 2019, no. 2019, pp.1-13.
https://search.emarefa.net/detail/BIM-1196071
Modern Language Association (MLA)
Xie, Yunxin…[et al.]. Towards Optimization of Boosting Models for Formation Lithology Identification. Mathematical Problems in Engineering No. 2019 (2019), pp.1-13.
https://search.emarefa.net/detail/BIM-1196071
American Medical Association (AMA)
Xie, Yunxin& Zhu, Chenyang& Lu, Yue& Zhu, Zhengwei. Towards Optimization of Boosting Models for Formation Lithology Identification. Mathematical Problems in Engineering. 2019. Vol. 2019, no. 2019, pp.1-13.
https://search.emarefa.net/detail/BIM-1196071
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1196071