An Adaptive NeuroFuzzy Inference System (ANFIS) is applied to model the potential of komatiite-hosted magmatic nickel sulfide mineral system in the greenstone belts of the Yilgarn Craton, Western Australia. A conceptual genetic model of the nickel-sulfide mineral system was used to identify the critical components and exploration criteria for nickel-sulfide deposits in the Yilgarn Craton at the camp scale. The exploration criteria, namely, potential nickel source rocks, potential pathways and sulfur saturation were represented in form of derivative GIS layers that were used as proxies for the exploration criteria. The derivative layers were used as model variables for developing a Takagi-Sugeno-type fuzzy inference system in the framework of nickel sulfide mineral systems. The premise and consequent parameters of the fuzzy inference system were estimated using a hybrid learning algorithm. About 70% of the 165 known deposits of the craton were used to train the models; the remaining 30% was used to validate the models and, therefore, had to be treated as if they had not been discovered. The ANFIS predicted about 70% of the validation deposits in prospective zones that occupy about 9% of the total area occupied by the greenstone belts in the craton. This preliminary study shows that conceptual models of mineral systems can be effectively represented by fuzzy inference systems. Moreover, by implementing a neural-network type learning algorithm, it is possible to objectively estimate the parameters of the fuzzy inference system from the spatial distribution of known mineral deposits.
Prospectivity modeling of Komatiite-hosted magmatic nickel sulfide mineral system in the Yilgarn Craton, Western Australia, using ANFIS
DEVENDRAN, AARTHI AISHWARYA
2011/2012
Abstract
An Adaptive NeuroFuzzy Inference System (ANFIS) is applied to model the potential of komatiite-hosted magmatic nickel sulfide mineral system in the greenstone belts of the Yilgarn Craton, Western Australia. A conceptual genetic model of the nickel-sulfide mineral system was used to identify the critical components and exploration criteria for nickel-sulfide deposits in the Yilgarn Craton at the camp scale. The exploration criteria, namely, potential nickel source rocks, potential pathways and sulfur saturation were represented in form of derivative GIS layers that were used as proxies for the exploration criteria. The derivative layers were used as model variables for developing a Takagi-Sugeno-type fuzzy inference system in the framework of nickel sulfide mineral systems. The premise and consequent parameters of the fuzzy inference system were estimated using a hybrid learning algorithm. About 70% of the 165 known deposits of the craton were used to train the models; the remaining 30% was used to validate the models and, therefore, had to be treated as if they had not been discovered. The ANFIS predicted about 70% of the validation deposits in prospective zones that occupy about 9% of the total area occupied by the greenstone belts in the craton. This preliminary study shows that conceptual models of mineral systems can be effectively represented by fuzzy inference systems. Moreover, by implementing a neural-network type learning algorithm, it is possible to objectively estimate the parameters of the fuzzy inference system from the spatial distribution of known mineral deposits.File | Dimensione | Formato | |
---|---|---|---|
Aarthi_thesis.pdf
accessibile in internet per tutti
Descrizione: Aarthi_thesis
Dimensione
4.74 MB
Formato
Adobe PDF
|
4.74 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/56912