A new strategy for spatial predictive mapping of mineral prospectivity: Automated hyperparameter tuning of random forest approach

Abstract

Machine learning algorithms (e.g., random forest (RF)) have recently been performed in data-driven mineral prospectivity mapping. These methods are highly sensitive to hyperparameter values, since the predictive accuracy of them can significantly increase when the optimized hyperparameters are predefined and then adjusted to training procedure. The main goal of this contribution is to propose a hybrid genetic-based RF model, namely GRF, which is able to automatically adjust the optimized hyperparameters of RF with the excellent predictive accuracy. Therefore, three primary parameters of RF comprising NT, NS and d, were well-tuned employing genetic algorithm (GA) in establishing an efficient RF model. The proposed GRF model and also conventional RF were tested on mineralization-related geo-spatial dataset and the predictive models were generated for comparing the accuracy of the proposed GRF model with that of RF. The input dataset (e.g., multi-element geochemical signature, geological-structural layer and hydrothermal alteration evidences) which acquired from Feizabad district, NE Iran, were translated into mappable targeting criteria in the form of four predictor maps. In addition, the locations of 13 known Cu–Au deposits as prospect data and the locations of 13 randomly selected non-prospect data were used as target variables to train the models. Three authentic validation measures, K-fold cross-validation, confusion matrix and success-rate curves, were employed to evaluate the overall performance of two predictive models. Experimental results suggested the superiority of GRF model over the RF, as the favorable areas derived by GRF model occupy only 9% of the study area while predicting 100% of the known deposits.