Group Method of Data Handling (GMDH) Lithology Identification Based on Wavelet Analysis and Dimensionality Reduction as Well Log Data Pre-Processing Techniques

Chuanbo Shen,Liang Wang,Xiangfeng Zhu,Solomon Asante-Okyere,Yao Yevenyo Ziggah

doi:10.3390/en12081509

Chuanbo Shen, Liang Wang + Show 3 more

Open Access

https://doi.org/10.3390/en12081509

Copy DOI

Abstract

Although the group method of data handling (GMDH) is a self-organizing metaheuristic neural network capable of developing a classification function using influential input variables, the results can be improved by using some pre-processing steps. In this paper, we propose a joint principal component analysis (PCA) and GMDH (PCA-GMDH) classifier method. We investigated well log data pre-processing techniques composed of dimensionality reduction (DR) and wavelet analysis (WA), using the southern basin of the South Yellow Sea as a case study, with the aim of improving the lithology classification accuracy of the GMDH. Our results showed that the dimensionality reduction method, which is composed of PCA and linear discriminant analysis (LDA), minimized the complexity of the classifier by reducing the number of well log suites to the relevant components and factors. On the other hand, the WA decomposed the well log signals into time-frequency wavelets for the GMDH algorithm. Of all the pre-processing methods, only the PCA was able to significantly increase the classification accuracy rate of the GMDH. Finally, the proposed joint PCA-GMDH classifier not only increased the accuracy but also was able to distinguish between all the classes of lithofacies present in the southern basin of the South Yellow Sea.

Highlights

Lithology identification is a fundamental process in reservoir characterization and formation evaluation
The self-organizing ability of the group method of data handling (GMDH) algorithm, whereby it does not rely on any human interference to adjust its model parameters, was successfully implemented to identify lithofacies present in the southern basin of the South Yellow Sea
This study explored the impact of the pre-processing techniques of principal component analysis (PCA) and linear discriminant analysis (LDA) as dimensional-reduction methods, and wavelet analysis, regarding the performance of GMDH lithology classification

Summary

Introduction

Lithology identification is a fundamental process in reservoir characterization and formation evaluation. Lithofacies are determined by either direct visualization of core samples or manual interpretation of well logs, by correlating similar physical characteristics of reservoir formations. These conventional methods for determining the lithology of the heterogeneous reservoir are time-consuming, labor intensive, and unreliable, since it is as a consequence of the intuition of geologists and log analysts [1,2,3,4]. To overcome these challenges, researchers have tried to introduce cross-plotting as a statistical method on well logs [5,6,7,8].

Methods

Findings

Discussion

Conclusion