Exploration feature selection applied to hybrid data integration modeling: Targeting copper-gold potential in central Iran
Introduction
Geologically and economically meaningful exploration targeting requires (a) a clear understanding of ore-forming processes and relevant recognition criteria at the scale of prospectivity modeling, (b) good-quality exploration data sets with consistent coverage over the study area, (c) preprocessing of exploration data sets to extract appropriate spatial proxies (or predictor patterns) for the recognition criteria, and lastly (d) selection of appropriate models for weighing the spatial proxies and integrating them. However, most published literature on prospectivity modeling focuses only on the last aspect — mathematical models. A variety of data integration models and their applications are described in the literature. Some of these models rely on expert knowledge for weighing spatial proxies while others use some measure of spatial association of known deposits with the spatial proxies; accordingly they have been broadly classified into knowledge-driven and data-driven. Fuzzy logic (e.g., An et al., 1991, Bonham-Carter, 1994, Carranza and Hale, 2001a, Carranza and Hale, 2001b, Lusty et al., 2012, Yousefi and Carranza, 2015, Yousefi et al., 2013), fuzzy-AHP (Abedi et al., 2013), interval valued fuzzy sets topsis (Jafari Rad and Busch, 2011), Boolean logic (e.g., Bonham-Carter, 1994), index overlay (e.g., Bonham-Carter, 1994) and Dempster–Shafer belief theory (An et al., 1994a, An et al., 1994b, Moon, 1990) are examples of knowledge-driven models used in mineral prospectivity. The most widely used data-driven models are weights of evidence (Asadi and Hale, 2000, Bonham-Carter et al., 1989, Ford and Hart, 2013), logistic regression (Carranza and Hale, 2001a, Carranza and Hale, 2001b, Mejía-Herrera et al., 2014), neural networks (Abedi and Norouzi, 2012, Porwal et al., 2004), evidential belief functions (Carranza, 2008, Carranza, 2014, Carranza and Hale, 2003), Bayesian network classifiers (Porwal et al., 2006) and support vector machine (Abedi et al., 2012, Yu et al., 2012, Zuo and Carranza, 2011). Porwal et al. (2004) implemented a fuzzy inference system in the framework of neural network using the ANFIS algorithm developed by Jang (1993). This model used expert-knowledge for weighing the spatial proxies, but the weights were fine-tuned using a neural network that was trained on known mineral occurrences. Theoretically, this approach leads to an optimum utilization of both expert-knowledge and deposit distribution pattern.
The present study applies the ANFIS algorithm to copper–gold prospectivity modeling in the poorly explored Urumieh–Dokhtar magmatic arc (UDMA) in central Iran. The ANFIS results are compared with the results of pure knowledge-driven fuzzy modeling in order to verify if hybrid modeling does indeed lead to improved results. The model inputs (spatial proxies) are derived from regional geological, geochemical, magnetic, and Aster satellite imagery data sets on the basis of recognition criteria of porphyry copper–gold, IOCG, hydrothermal Cu–Au vein and skarn mineralizations.
Section snippets
Study area
The study area is a sparsely vegetated, semi-arid, mountainous region that covers some 13,600 km2 of the central part of the UDMA in central Iran (Fig. 1). The UDMA is the most important volcanic arc of Iran that extends about 2000 km in a NW–SE direction in the central part of the Tethyan metallogenic belt. This arc hosts world class porphyry copper deposits such as Sar-Cheshmeh, Songun, Meiduk, Kahang, Darezar, Darreh-Zerreshk and Dalli (Ayati et al., 2013, Hezarkhani, 2006, Hezarkhani and
Geodynamic and metallogenic setting of UDMA
The Zagros orogenic belt of Iran is part of the central Tethyan region, located between the Arabian and Eurasian plates. The Tethyan metallogenic belt extends across central and southeast Europe, Turkey, Iran, Pakistan, through the Himalayan region and southeast Asia. A number of large deposits have been discovered in the central Tethyan belt, which passes through Turkey, Iran and Pakistan, even though the belt is relatively poorly explored and is difficult to access. Some of the world class
Copper–gold mineralization in central UDMA
The known copper and gold mineralizations in central UDMA are mainly of porphyry and IOCG types, associated with magmatic hydrothermal processes. Porphyry and IOCG deposits have several similarities and are the major sources of copper and gold in the world (Richards and Mumin, 2013). The porphyry deposits are characterized by multiple phases of porphyritic intrusions and extensive hydrothermal alteration. In exploration data sets, they are characterized by magnetic highs and anomalous Cu, Au,
Regional-scale recognition criteria
Mineral systems are often used to define recognition criteria for regional exploration (Porwal and Kreuzer, 2010). Porphyry Cu–Au and IOCG mineralizations are the prominent mineral systems in central UDMA area. There are also less-important hydrothermal Cu–Au–Ag vein and Cu–Ag–Fe skarn mineralizations in the area. To identify the recognition criteria for regional-scale Cu–Au exploration of the area, the key geologic controls, geochemical characteristics and magnetic signatures of the prominent
Regional-scale exploration data set
A GIS database of the known porphyry Cu–Au and IOCG-type mineral occurrences and the exploration data sets (including geology, remote sensing, geophysics and geochemistry) for central UDMA area was established. The available regional exploration data set covering an area of 13,628 km2 comprises six shape files of geological maps (1:100,000 scale), eight advanced spaceborne thermal infrared (ASTER) and enhanced Landsat thematic mapper (ETM +) scenes, ICP analytical results of 14,390 stream
Exploration feature selection
Favorable spatial proxies of the regional-scale recognition criteria including host lithologies and structures, hydrothermal alterations, stream sediment geochemical anomalies, and magnetic signatures were selected from the reclassified geologic maps and the processed Aster satellite imagery, stream sediment geochemical and aeromagnetic data, respectively.
Data integration
The input data for integrated prospectivity modeling of Cu–Au deposits in the study area include: lithological map, the multi-element catchment basin geochemical anomalies, lineament density map generated from the 1:100,000 geological maps, major basement lineaments generated from total magnetic intensity map, fuzzified RTP magnetic anomalies (using a large membership function) characterizing the potential copper–gold host intrusions and other lithological units, OH-bearing minerals, chloritic
Discussion and conclusions
Detailed geological characterization of the prominent mineralization in the area was used in conjunction with the generic genetic models of the IOCG and porphyry copper–gold deposits to identify the recognition criteria and represented as evidential layers for inputting to mineral prospectivity models. The evidential layers were ranked by expert geologists and integrated using fuzzy and neuro-fuzzy systems to delineate Cu–Au target areas for follow-up exploration. The target areas in the final
Acknowledgment
We would like to thank the Geological Survey of Iran and Dorsa Pardazeh Mining Company in providing most of the exploration data used in this research. Thanks are also extended to the two anonymous reviewers for their constructive comments. This is contribution 521 from the ARC Centre of Excellence for Core to Crust Fluid Systems (www.CCFS.mq.edu.au) and an IGCP/SIDA-600 contribution.
References (84)
- et al.
Integration of various geophysical data with geological and geochemical data to determine additional drilling for copper exploration, Department of Mining Engineering, College of Engineering, University of Tehran, Iran
J. Appl. Geophys.
(2012) Tectonics of the Zagros orogenic belt of Iran, new data and interpretations
Tectonophysics
(1994)- et al.
Exploratory data analysis and C–A fractal model applied in mapping multi-element soil anomalies for drilling: a case study from Sari Gunay epithermal gold deposit, NW Iran
J. Geochem. Explor.
(2014) Analysis and mapping of geochemical anomalies using logratio-transformed stream sediment data with censored values
J. Geochem. Explor.
(2011)- et al.
A catchment basin approach to the analysis of geochemical–geological data from Albay province, Philippines
J. Geochem. Explor.
(1997) - et al.
Evidential belief functions for data-driven geologically constrained mapping of gold potential, Baguio district, Philippines
Ore Geol. Rev.
(2003) External sulphur in IOCG mineralization: implications on definition and classification of the IOCG clan
Ore Geol. Rev.
(2013)- et al.
The separation of geochemical anomalies from background by fractal methods
J. Geochem. Explor.
(1994) - et al.
Univariate statistical analysis of environmental (compositional) data: problems and possibilities
Sci. Total Environ.
(2009) - et al.
The bivariate statistical analysis of environmental (compositional) data
Sci. Total Environ.
(2010)
Mineral potential mapping in frontier regions: a Mongolian case study
Ore Geol. Rev.
Computer aided diagnosis system for Alzheimer disease using brain diffusion tensor imaging features selected by Pearson's correlation
Neurosci. Lett.
From andesitic volcanism to the formation of a porphyry Cu–Au mineralizing magma chamber: the Farallo'n Negro Volcanic Complex, northwestern Argentina
J. Volcanol. Geotherm. Res.
Hydrothermal evolution of the Sarcheshmeh porphyry Cu–Mo deposit, Iran: evidence from fluid inclusion
J. Asian Earth Sci.
Geological characteristics and tectonic setting of proterozoic iron oxide (Cu, U, Au and REE) deposits
Precambrian Res.
Towards automatic lithological classification from remote sensing data using support vector machines
Comput. Geosci.
An experiment in linguistic synthesis with a fuzzy logic controller
Int. J. Man Mach. Stud.
Distribution of porphyry deposits in the Eurasian continent and their corresponding tectonic settings
J. Asian Sci.
Introduction to the special issue: mineral prospectivity analysis and quantitative resource estimation
Ore Geol. Rev.
Porphyry Cu–Mo–(Au) mineralization: the age and relationship with igneous rock complexes of the Borgulikan ore field (upper-Amur region)
Russ. Geol. Geophys.
Geochemical mapping using a geomorphologic approach based on catchments
J. Geochem. Explor.
Geology of the postcollisional porphyry copper–molybdenum deposit at Qulong, Tibet
Ore Geol. Rev.
Fuzzification of continuous-value spatial evidence for mineral prospectivity mapping
Comput. Geosci.
Geochemical mineralization probability index (GMPI): a new approach to generate enhanced stream sediment geochemical evidential map for increasing probability of success in mineral potential mapping
J. Geochem. Explor.
Weighted drainage catchment basin mapping of stream sediment geochemical anomalies for mineral potential mapping
J. Geochem. Explor.
Support vector machine: a tool for mapping mineral prospectivity
Comput. Geosci.
Support vector machine for multi-classification of mineral prospectivity areas
Comput. Geosci.
Application of fuzzy AHP method to integrate geophysicaldata in a prospect scale, a case study: Seridune copper deposit
Boll. Geofis. Teor. Appl.
Mineral chemistry of hydrothermal biotite from the Kahang porphyry copper deposit (NE Isfahan), Central Province of Iran
Ore Geol. Rev.
Application of 393 power-spectrum-volume fractal method for detecting hypogene, supergene enrichment, leached and 394 barren zones in Kahang Cu porphyry deposit, central Iran
J. Geochem. Explor.
Regional stratigraphy of the Zagros fold–thrust belt of Iran and its proforeland evolution
Am. J. Sci.
Mineralogy and Geochemistry of the Aftabru Poly Metal Prospect, Markazi Province
Application of fuzzy set theory for integration of geological, geophysical and remote sensing data
Can. J. Explor. Geophys.
An object-oriented knowledge representation structure for exploration data integration
Nonrenew. Resour.
Uncertainty management in integration of exploration data using the belief function
Nonrenew. Resour.
The Genesis of Zarshuran Sediment-hosted Gold Deposit Applied in a Mineral Exploration GIS in Iran
Final exploration report of Dalli porphyry Cu–Au deposit, Markazi province
A predictive GIS model for mapping potential gold and base metal mineralization in Takab area, Iran
Comput. Geosci.
Neogene Magmatism and Related Hydrothermal Alterations in NE of Arak (Dalli Cu–Au Deposit)
Chemical characteristics and composition of hydrothermal biotite from the Dalli porphyry copper prospect, Arak, central province of Iran
Mineral. Petrol.
Petrology and geochemistry of calc-alkaline volcanic and subvolcanic rocks, Dalli porphyry copper–gold deposit, Markazi province, Iran
International Geology Review
Aspects of magmatic–hydrothermal evolution of Kahang porphyry copper deposit, central Iran
Arab. J. Geosci.
Cited by (42)
Data-driven logistic function for weighting of geophysical evidence layers in mineral prospectivity mapping
2023, Journal of Applied Geophysics3D analysis of catchment basins by incorporating modified dilution correction equations in geochemical anomaly delineation
2020, Journal of Geochemical ExplorationIdentification and application of a Carlin-type gold mineral system for exploration targeting in the Takab geothermal basin, NW Iran
2020, Ore Geology ReviewsCitation Excerpt :Various methods containing band ratios, spectral angle mapper (SAM) and least square fit (Ls- Fit) (Honarmand et al., 2012; Feizi and Mansuri, 2013; Asadi et al., 2015) were applied to the ASTER and ETM+ satellite imagery data to locate these alterations. Phyllic and argillic alterations were mapped from SWIR and VNIR Landsat ETM+ spectral bands applying LS-Fit method (Mars and Rowan, 2006; Feizi and Mansuri, 2013; Asadi et al., 2015). Propyllitic alteration (Chlorite and epidote) and silicification were mapped by processing SWIR and TIR bands of the ASTER data using SAM and band rationing, respectively (Pour and Hashim, 2012; Honarmand et al., 2012; Alimohammadi et al. 2015; Moghtaderi et al., 2017).