{"title":"Targeting porphyry Cu deposits in the Chahargonbad region of Iran: A joint application of deep belief networks and random forest techniques","authors":"Majid Keykhay-Hosseinpoor , Alok Porwal , Kalimuthu Rajendran","doi":"10.1016/j.chemer.2024.126155","DOIUrl":null,"url":null,"abstract":"<div><div>Mineral prospectivity modeling (MPM) is a valid and progressively accepted predictive tool for mapping reproducible potential mineral exploration targets. In this study, a hybrid approach combining unsupervised deep belief networks with supervised random forest (DBN-RF) is performed to delineate potential exploration targets for porphyry Cu deposits in the Chahargonbad region of Iran. Firstly, a mineral system model for porphyry Cu deposits is established, and relevant targeting criteria are delineated based on comprehensive exploration datasets. Subsequently, within this hybrid framework, the DBN extracts deep implicit feature information, which is then utilized as input for the RF. The comparative results on the performance of the hybrid model and the RF model trained by the primary targeting criteria, in terms of the improved prediction-area plot, demonstrate that the DBN-RF prospectivity model outperformed the RF-generated model with an overall efficiency of 0.53. This hybrid model accurately identified 81.97 % of known Cu deposits within an investigation area of 18.03 %, with primary trends aligned with the primary faults and volcanic units of the region. This study demonstrates effective performance of DBN-RF in identifying exploration targets for porphyry Cu deposits at regional scale and also highlights the potential of deep learning-based methods for successful MPM.</div></div>","PeriodicalId":55973,"journal":{"name":"Chemie Der Erde-Geochemistry","volume":"84 4","pages":"Article 126155"},"PeriodicalIF":2.6000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chemie Der Erde-Geochemistry","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0009281924000801","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOCHEMISTRY & GEOPHYSICS","Score":null,"Total":0}
引用次数: 0
Abstract
Mineral prospectivity modeling (MPM) is a valid and progressively accepted predictive tool for mapping reproducible potential mineral exploration targets. In this study, a hybrid approach combining unsupervised deep belief networks with supervised random forest (DBN-RF) is performed to delineate potential exploration targets for porphyry Cu deposits in the Chahargonbad region of Iran. Firstly, a mineral system model for porphyry Cu deposits is established, and relevant targeting criteria are delineated based on comprehensive exploration datasets. Subsequently, within this hybrid framework, the DBN extracts deep implicit feature information, which is then utilized as input for the RF. The comparative results on the performance of the hybrid model and the RF model trained by the primary targeting criteria, in terms of the improved prediction-area plot, demonstrate that the DBN-RF prospectivity model outperformed the RF-generated model with an overall efficiency of 0.53. This hybrid model accurately identified 81.97 % of known Cu deposits within an investigation area of 18.03 %, with primary trends aligned with the primary faults and volcanic units of the region. This study demonstrates effective performance of DBN-RF in identifying exploration targets for porphyry Cu deposits at regional scale and also highlights the potential of deep learning-based methods for successful MPM.
期刊介绍:
GEOCHEMISTRY was founded as Chemie der Erde 1914 in Jena, and, hence, is one of the oldest journals for geochemistry-related topics.
GEOCHEMISTRY (formerly Chemie der Erde / Geochemistry) publishes original research papers, short communications, reviews of selected topics, and high-class invited review articles addressed at broad geosciences audience. Publications dealing with interdisciplinary questions are particularly welcome. Young scientists are especially encouraged to submit their work. Contributions will be published exclusively in English. The journal, through very personalized consultation and its worldwide distribution, offers entry into the world of international scientific communication, and promotes interdisciplinary discussion on chemical problems in a broad spectrum of geosciences.
The following topics are covered by the expertise of the members of the editorial board (see below):
-cosmochemistry, meteoritics-
igneous, metamorphic, and sedimentary petrology-
volcanology-
low & high temperature geochemistry-
experimental - theoretical - field related studies-
mineralogy - crystallography-
environmental geosciences-
archaeometry