Skip to Main Content
Skip Nav Destination
GEOREF RECORD

Identification of multi-mineral-species geochemical anomalies using BME and the spectrum separable module-constrained variational autoencoder

Zhao Bo, Deng Dongmin, Zhang Dehui, Tang Kun, Tang Panpan and An Lin
Identification of multi-mineral-species geochemical anomalies using BME and the spectrum separable module-constrained variational autoencoder
Geochemistry - Exploration, Environment, Analysis (February 2024) 24 (1)

Abstract

This study presented a dual-drive multi-mineral-species anomaly detection system which involves the combined use of BME (Bayesian Maximum Entropy), SSM (Spectral Separable Module), High-Order Factor Analysis, a geologically constrained loss function, as well as a mixed Gaussian distribution-based thresholding algorithm, attaching to a deep CAE (Convolutional Auto-Encoder). We have achieved several firsts rarely considered in the existing literature, e.g., previous works focus mainly on separating single-mineral-species but multi-elemental anomalies, while we attempted to recognize the multi-mineral-species anomalies; previous works pay more attention to data, while we answered how to discover the ore-related correlations hidden within the input data; previous works fail to integrate soft data in a quantitative fashion, while we achieved that by capitalizing on BME and the stratigraphic combination entropy. A series of comparative experiments have demonstrated its advantages over other state-of-the-art approaches. Finally, we obtained a mineral-occurrence identification rate (delta ) ranging from 36.87% to 61.46% versus the anomaly area ranging from 33.75% to 55.38% for each metalliferous anomaly division.


ISSN: 1467-7873
EISSN: 2041-4943
Serial Title: Geochemistry - Exploration, Environment, Analysis
Serial Volume: 24
Serial Issue: 1
Title: Identification of multi-mineral-species geochemical anomalies using BME and the spectrum separable module-constrained variational autoencoder
Affiliation: Nanhu Laboratory, Research Center of Big Data Technology, Jiaxing, China
Published: 20240229
Text Language: English
Publisher: Geological Society Publishing House, London, United Kingdom
References: 50
Accession Number: 2024-022103
Categories: Economic geology, general, deposits
Document Type: Serial
Bibliographic Level: Analytic
Illustration Description: illus. incl. 7 tables, geol. sketch map
N33°00'00" - N34°49'60", E108°00'00" - E111°00'00"
Secondary Affiliation: Yangtze Normal University, School of Green Intelligent Environment, CHN, ChinaChina University of Geosciences, School of Resources, CHN, ChinaShaanxi Geo-Mineral Comprehensive Geological Brigade, CHN, China
Country of Publication: United Kingdom
Secondary Affiliation: GeoRef, Copyright 2024, American Geosciences Institute. Reference includes data from GeoScienceWorld, Alexandria, VA, United States. Reference includes data from The Geological Society, London, London, United Kingdom
Update Code: 202413
Close Modal

or Create an Account

Close Modal
Close Modal