Incorporating the genetic and firefly optimization algorithms into K-means clustering method for detection of porphyry and skarn Cu-related geochemical footprints in Baft district, Kerman, Iran

Abstract

For the purpose of multi-element geochemical modeling of stream sediment data, we investigate the use of unsupervised clustering analysis (CA). For the various reasons including straightforward implementation, fast computation, and scaling to big dataset, the K-means (KM) algorithm was implemented to cluster the geochemical data to reveal anomalous populations linked to porphyry and skarn Cu deposits in Baft district, NE Iran. However, one of the biggest disadvantages of KM method is the randomly selection of cluster centroids which may increase the systemic uncertainty in unsupervised geochemical modeling and also run time. To address this, genetic (GA) and firefly (FA) metaheuristic optimization algorithms were incorporated into the KM method (namely GKM and FKM models) for determination of cluster centroids, and then, optimal definition of geospatial patterns of anomaly-background classes using clr-transformed values of stream sediment geochemical data. To do so, sample catchment basins (SCBs) of anomalous geochemical dataset were used to spatially map the anomaly populations derived from KM, GKM and FKM methods. We have used the advantages of quantitative evaluation measures namely normalized density index (NDI) and success-rate curves to assess the effectiveness of multi-element geochemical anomaly in determining exploratory targets. The results not only affirms that CA is a useful method to decompose the geochemical anomaly-background populations, but also hybridization of clustering methods via optimization algorithms can efficiently increase the certainty of mineralized zones to be used in further exploration stages.