Exploration
Feridon Ghadimi; Arman Ghadimi
Abstract
The Geochemical Mineralization Probability Index (GMPI) represents a phase weight assigned to each geochemical stream sediment sample for individual indicator components. In this framework, the weights of the evidence map classes are determined based on the factor scores (FS) derived from factor analysis ...
Read More
The Geochemical Mineralization Probability Index (GMPI) represents a phase weight assigned to each geochemical stream sediment sample for individual indicator components. In this framework, the weights of the evidence map classes are determined based on the factor scores (FS) derived from factor analysis for each indicator component. A wide range of direct and indirect approaches has been proposed to delineate prospective zones for mineral exploration; however, many of these methods are associated with substantial time and financial costs. Accordingly, this study aims to evaluate the performance of an Artificial Neural Network (ANN) model and to compare its predictive capability with that of conventional model-architecture-based approaches. In this research, a hybrid Artificial Neural Network–Biogeography-Based Optimization (ANN–BBO) model is developed to estimate the GMPI. The dataset used for model training and validation comprises geochemical concentrations of Au, Cu, Pb, Zn, Ag, Mo, W, and Sn obtained from 109 stream sediment samples collected in the Zaghar area. Biogeography-Based Optimization (BBO) is employed to optimize the ANN training process by adaptively adjusting its parameters to enhance predictive performance. The proposed ANN–BBO model achieved a Mean Squared Error (MSE) of 0.0221 and a coefficient of determination (R²) of 0.8244, indicating satisfactory predictive accuracy. Furthermore, the model demonstrated robust generalization capability, maintaining reliable predictive performance despite the considerable geochemical variability observed within the stream sediment dataset. The results of the sensitivity analysis reveal that Pb and Ag exert the most significant influence on the prediction of geochemical anomalies within the study area.
Z. Bayatzadeh Fard; F. Ghadimi; H. Fattahi
Abstract
Determining the distribution of heavy metals in groundwater is important in developing appropriate management strategies at mine sites. In this paper, the application of artificial intelligence (AI) methods to data analysis,namely artificial neural network (ANN), hybrid ANN with biogeography-based optimization ...
Read More
Determining the distribution of heavy metals in groundwater is important in developing appropriate management strategies at mine sites. In this paper, the application of artificial intelligence (AI) methods to data analysis,namely artificial neural network (ANN), hybrid ANN with biogeography-based optimization (ANN-BBO), and multi-output adaptive neural fuzzy inference system (MANFIS) to estimate the distribution of heavy metals in groundwater of Lakan lead-zinc mine is demonstrated.For this purpose, the contamination groundwater resources were determined using the existing groundwater quality monitoring data, and several models were trained and tested using the collected data to determine the optimum model that used three inputs and four outputs. A comparison between the predicted and measured data indicated that the MANFIS model had the mostpotential to estimate the distribution of heavy metals in groundwater with a high degree of accuracy and robustness.
