Exploration
Ahmadreza Erfan; Saeed Soltani Mohammad; Maliheh Abbaszadeh
Abstract
Machine learning (ML) has significantly transformed multiple disciplines, including mineral resource evaluation in mining engineering, by facilitating more accurate and efficient estimation methods. Ensemble methods, as a fundamental component of modern machine learning, have emerged as powerful ...
Read More
Machine learning (ML) has significantly transformed multiple disciplines, including mineral resource evaluation in mining engineering, by facilitating more accurate and efficient estimation methods. Ensemble methods, as a fundamental component of modern machine learning, have emerged as powerful tools that robust techniques that integrate multiple predictive models to improve performance beyond that of any individual learner. This study proposes a novel ensemble method for estimating ore grades by localizing the base learner weights in ensemble method. Ordinary kriging, inverse distance weighting, k-nearest neighbors, support vector regression, and artificial neural networks have been used as the base learners of the algorithm. In ML base learners, coordinates (easting, northing and elevation) of samples have been defined as input nodes and grade has been defined as target. The proposed method has been validated for predicting the copper grade (Cu%) in Darehzar porphyry deposit. The performance of proposed method has been by individual base learners and famous ensemble methods. This comparison shows that performance of proposed method is better than other ones. The findings highlight the necessity of adapting ensemble methods to address spatial variability in geological data, thereby establishing a robust framework for ore grade estimation.
Exploitation
S. Soltani-Mohammadi; A. Soltani; B. Sohrabian
Abstract
Due to the nature of the geological and mining activities, different input parameters in the grade estimation and mineral resource evaluation are always tainted with uncertainties. It is possible to investigate the uncertainties related to the measurements and parameters of the variogram model using ...
Read More
Due to the nature of the geological and mining activities, different input parameters in the grade estimation and mineral resource evaluation are always tainted with uncertainties. It is possible to investigate the uncertainties related to the measurements and parameters of the variogram model using the fuzzy kriging method instead of the kriging method. The fuzzy kriging theory has already been the subject of relatively various research studies but the main weak point in such studies is that the results of the fuzzy estimations are not used in decision-making and planning. A very common, but key, tool of decision-making for mining engineers is the tonnage-average grade models. Under conditions where measurements or/and variogram model parameters are tainted with uncertainties, the tonnage-average grade model will be uncertain as well. Therefore, it is necessary to use the fuzzy tonnage-grade model instead of the crisp ones, and the next analysis steps and decision-makings are done accordingly. In this paper, the computational principles of the fuzzy tonnage-average grade curve and a case study regarding its usage are presented.
