Mutual complement between statistical and neural network approaches for rock magnetism data analysis

Interpretation of magnetic phenomena in rock magnetism requires a good understanding in relationship between magnetic susceptibility and magnetic minerals, particularly magnetite, contained in rocks. Previous studies emphasized on describing such a correlation using a sole expression through statist...

Full description

Bibliographic Details
Main Authors: Guo, W., Li, M., Whymark, G., Li, Zheng-Xiang
Format: Journal Article
Published: Elsevier 2009
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/9733
_version_ 1848746034754224128
author Guo, W.
Li, M.
Whymark, G.
Li, Zheng-Xiang
author_facet Guo, W.
Li, M.
Whymark, G.
Li, Zheng-Xiang
author_sort Guo, W.
building Curtin Institutional Repository
collection Online Access
description Interpretation of magnetic phenomena in rock magnetism requires a good understanding in relationship between magnetic susceptibility and magnetic minerals, particularly magnetite, contained in rocks. Previous studies emphasized on describing such a correlation using a sole expression through statistical analysis. The resultant correlations are generally useful only in qualitative interpretation, but too coarse to simulate quantitative solutions. In this paper, we combine the correlation analysis with neural network techniques to not only identify the correlations between susceptibility and magnetite in rocks but also simulate accurate susceptibilities with respect to the magnetite contents provided. Our study has demonstrated that multilayer perceptron models are capable of producing accurate mappings between susceptibility and magnetite in rocks. However, correlation analysis provides qualitative interpretation for rock magnetism data in identifying the patterns of magnetic behaviours of the rocks. Inquantitative simulation, if the required accuracy is not restricted, a general MLP model with existenceof noises in training data is the first choice because it does not require statistical data pre-processingfor establishing the NN model. If the simulation is to provide solutions as accurate as possible, theMLP model must be trained by noise-filtered datasets. The noise filtering is based on the preliminary correlation analysis. Therefore, these two approaches are mutually complementary, rather than competitive to each other.
first_indexed 2025-11-14T06:26:50Z
format Journal Article
id curtin-20.500.11937-9733
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:26:50Z
publishDate 2009
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-97332017-09-13T16:06:55Z Mutual complement between statistical and neural network approaches for rock magnetism data analysis Guo, W. Li, M. Whymark, G. Li, Zheng-Xiang Neural networks Multilayer perceptron Correlation analysis Rock magnetism Interpretation of magnetic phenomena in rock magnetism requires a good understanding in relationship between magnetic susceptibility and magnetic minerals, particularly magnetite, contained in rocks. Previous studies emphasized on describing such a correlation using a sole expression through statistical analysis. The resultant correlations are generally useful only in qualitative interpretation, but too coarse to simulate quantitative solutions. In this paper, we combine the correlation analysis with neural network techniques to not only identify the correlations between susceptibility and magnetite in rocks but also simulate accurate susceptibilities with respect to the magnetite contents provided. Our study has demonstrated that multilayer perceptron models are capable of producing accurate mappings between susceptibility and magnetite in rocks. However, correlation analysis provides qualitative interpretation for rock magnetism data in identifying the patterns of magnetic behaviours of the rocks. Inquantitative simulation, if the required accuracy is not restricted, a general MLP model with existenceof noises in training data is the first choice because it does not require statistical data pre-processingfor establishing the NN model. If the simulation is to provide solutions as accurate as possible, theMLP model must be trained by noise-filtered datasets. The noise filtering is based on the preliminary correlation analysis. Therefore, these two approaches are mutually complementary, rather than competitive to each other. 2009 Journal Article http://hdl.handle.net/20.500.11937/9733 10.1016/j.eswa.2008.11.045 Elsevier restricted
spellingShingle Neural networks
Multilayer perceptron
Correlation analysis
Rock magnetism
Guo, W.
Li, M.
Whymark, G.
Li, Zheng-Xiang
Mutual complement between statistical and neural network approaches for rock magnetism data analysis
title Mutual complement between statistical and neural network approaches for rock magnetism data analysis
title_full Mutual complement between statistical and neural network approaches for rock magnetism data analysis
title_fullStr Mutual complement between statistical and neural network approaches for rock magnetism data analysis
title_full_unstemmed Mutual complement between statistical and neural network approaches for rock magnetism data analysis
title_short Mutual complement between statistical and neural network approaches for rock magnetism data analysis
title_sort mutual complement between statistical and neural network approaches for rock magnetism data analysis
topic Neural networks
Multilayer perceptron
Correlation analysis
Rock magnetism
url http://hdl.handle.net/20.500.11937/9733