Stacking: A novel data-driven ensemble machine learning strategy for prediction and mapping of Pb-Zn prospectivity in Varcheh district, west Iran

Abstract

Various ensemble machine learning techniques have been widely studied and implemented to construct the predictive models in different sciences, including bagging, boosting, and stacking. However, bagging and boosting concentrate on minimizing variance or bias, stacking techniques aimed at reducing both by identifying the optimal integration of base learners. Moreover, while most ensemble methods simply combine identical machine learning models, stacking utilizes a meta-machine learning model to combine different base learning models, aiming to enhance the overall accuracy of generalization. Therefore, this research showed the utilization of stacking, an ensemble approach, to develop mineral prospectivity models for Pb-Zn mineralization in the Varcheh District, west Iran. To end this, various exploration evidence layers, including geochemical data, remote sensing data, geological and tectonic controls were used to construct the stacking structure. In the following, a set of five base learners were applied, containing support vector regression (SVR) using RBF, linear and polynomial kernels, the K-nearest neighbor (KNN), and linear regression. Ridge, SVR-RBF and XGBoost were used as a meta-learner to integrate the outputs of basic learners. To measure how well each model performed, ROC, F1-score and Precision metrics was carried out. Moreover, compared to the separate algorithms, the stacking-based ensemble model showed a better prediction accuracy. The findings of this study demonstrated that the ensemble model based on stacking achieved a 95% prediction rate for Pb-Zn deposits, covering only 9% of the study area. As a result, this model holds promise as an effective tool for predicting mineral prospectivity in other study areas, regardless of whether they exhibit similar or different types of mineralization.