Recognition of multivariate geochemical anomalies using a geologically-constrained variational autoencoder network with spectrum separable module – A case study in Shangluo District, China

This study has developed a novel variational autoencoder architecture by incorporating the spectrum separable module, termed SSM-VAE, so as to recognize the multi-mineral-species geochemical patterns over the Shangluo district, central China, and then facilitate a better understanding of the regiona...

Full description

Saved in:
Bibliographic Details
Published in:Applied geochemistry Vol. 156; p. 105765
Main Authors: Zhao, Bo, Zhang, Dehui, Tang, Panpan, Luo, Xiaoyan, Wan, Haoming, An, Lin
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.09.2023
Subjects:
algorithms
case studies
China
Deep learning
factor analysis
geochemistry
Geology
mineralization
Multivariate anomaly
Spectrum separable module
China
Deep learning
Multivariate anomaly
Geology
Spectrum separable module
ISSN:0883-2927, 1872-9134
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study has developed a novel variational autoencoder architecture by incorporating the spectrum separable module, termed SSM-VAE, so as to recognize the multi-mineral-species geochemical patterns over the Shangluo district, central China, and then facilitate a better understanding of the regional metallogenesis. The primary advantage of SSM-VAE is its ability to explore the interlayer correlations and then integrate them into the reconstructed features, which greatly improved the geological interpretability of the model products. In the training process, a hybrid loss function with a geologically-constrained term derived from the fractal analysis was designed to guide the model to focus on anomalies related to mineralization. Afterward, the factor analysis together with the EM-MML thresholding algorithm were integrated as a post-processing tool. Finally, the mineral-spot identification rate (δ) versus the size of the anomalous area (S) are used to validate the ore-bearing potential of different anomaly divisions. Comparing to other state-of-the-art models without regard to the interlayer correlations, SSM-VAE can produce well-zoned, mineral species-specific, and more metalliferous anomalous patches. To be specific, we separated out 10 zoned anomaly divisions, and on average, when S = 1% there are 8.5013 mineral spots falling within. •Our SSM-VAE is designed to model the correlations among the input geochemical data-layers.•A hybrid loss function with a geologically-constrained term was incorporated into SSM-VAE and its training process.•Our SSM-VAE shows a clear advantage in producing well-zoned, mineral species-specific, and metalliferous anomalous patches.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0883-2927
1872-9134
DOI:10.1016/j.apgeochem.2023.105765