A Coarse-to-Fine Approach for Intelligent Logging Lithology Identification with Extremely Randomized Trees
- PDF / 1,742,200 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 85 Downloads / 195 Views
A Coarse-to-Fine Approach for Intelligent Logging Lithology Identification with Extremely Randomized Trees Yunxin Xie1 · Chenyang Zhu2 Zhengwei Zhu1
· Runshan Hu2 ·
Received: 29 April 2020 / Accepted: 27 July 2020 © The Author(s) 2020
Abstract Lithology identification is vital for reservoir exploration and petroleum engineering. Recently, there has been growing interest in using an intelligent logging approach for lithology classification. Machine learning has emerged as a powerful tool in inferring lithology types with the logging curves. However, well logs are susceptible to logging parameter manual entry, borehole conditions and tool calibrations. Most studies in the field of lithology classification with machine learning approaches have focused only on improving the prediction accuracy of classifiers. Also, a model trained in one location is not reusable in a new location due to different data distributions. In this paper, a unified framework is provided for training a multi-class lithology classification model for a data set with outlier data. In this paper, a coarse-to-fine framework that combines outlier detection, multi-class classification with an extremely randomized tree-based classifier is proposed to solve these issues. An unsupervised learning approach is used to detect the outliers in the data set. Then a coarse-to-fine inference procedure is used to infer the lithology class with an extremely randomized tree classifier. Two real-world data sets of well-logging are used to demonstrate the effectiveness of the proposed framework. Comparisons are conducted with some baseline machine learning classifiers, namely random forest, gradient tree boosting, and xgboosting. Results show that the proposed framework has higher prediction accuracy in sandstones compared with other approaches. Keywords Lithology classification · Ensemble methods · Outlier detection
B
Chenyang Zhu [email protected]
1
Changzhou University, Changzhou, China
2
University of Southampton, Southampton, UK
123
Math Geosci
1 Introduction The role of lithology identification in mineral exploration and petroleum exploration has received increased attention across several disciplines in recent years. As the basis of reservoir characteristics research and geological modeling, lithology identification provides a reliable basis for measuring the spatial distribution of the mineral area (Rider 1986). Lithology identification is used in fields such as reservoir characterization, reservoir evaluation, and reservoir modeling in petroleum development and engineering. Thus it is vital to understand the lithology of the target layer in the geology and petroleum engineering industries. At present, approaches such as gravity, well-logging, seismic, remote sensing, electromagnetic and geophysics, have been used in lithology identification. Well-logging is one of the most common practices for lithology identification in petroleum exploration. The geological information carried by well-logging data is an essential source for determining gas rese
Data Loading...
