Discrimination of Mineralized Rock Types in a Copper-Rich Volcanogenic Massive Sulfide Deposit Through Fast Independent Component and Factor Analysis

Hajsadeghi, Saeid; Asghari, Omid; Mirmohammadi, Mirsaleh; Meshkani, Seyed Ahmad

doi:10.1007/s11053-019-09499-0

Cited by 4 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is definitely noteworthy that a combination of machine learning methods with geostatistical methods can optimize the geochemical modeling results [9]. For instance, it is essential to determine statistical communities when applying the linear discriminant analysis (LDA) algorithm [42,43]. Threshold limits of each community can be calculated with various methods, such as k-means clustering or concentration-area (C-A) fractal analysis.…”

Section: Introductionmentioning

confidence: 99%

Geochemical Modeling of Copper Mineralization Using Geostatistical and Machine Learning Algorithms in the Sahlabad Area, Iran

Shirazi,

Hezarkhani,

Shirazy

et al. 2023

Minerals

View full text Add to dashboard Cite

Analyzing geochemical data from stream sediment samples is one of the most proactive tools in the geochemical modeling of ore mineralization and mineral exploration. The main purpose of this study is to develop a geochemical model for prospecting copper mineralization anomalies in the Sahlabad area, South Khorasan province, East Iran. In this investigation, 709 stream sediment samples were analyzed using inductively coupled plasma mass spectrometry (ICP-MS), and geostatistical and machine learning techniques. Subsequently, hierarchical analysis (HA), Spearman’s rank correlation coefficient, concentration–area (C–A) fractal analysis, Kriging interpolation, and descriptive statistics studies were performed on the geochemical dataset. Machine learning algorithms, namely K-means clustering, factor analysis (FA), and linear discriminant analysis (LDA) were employed to deliver a comprehensive geochemical model of copper mineralization in the study area. The identification of trace elements and the predictor composition of copper mineralization, the separation of copper geochemical communities, and the investigation of the geochemical behavior of copper vs. its trace elements were targeted and accomplished. As a result, the elements Ag, Mo, Pb, Zn, and Sn were distinguished as trace elements and predictors of copper geochemical modeling in the study area. Additionally, geochemical anomalies of copper mineralization were identified based on trace elements. Conclusively, the nonlinear behavior of the copper element versus its trace elements was modeled. This study demonstrates that the integration and synchronous use of geostatistical and machine learning methods can specifically deliver a comprehensive geochemical modeling of ore mineralization for prospecting mineral anomalies in metallogenic provinces around the globe.

show abstract

Section: Introductionmentioning

confidence: 99%