Accurate prediction of mineral grades is a fundamental step in mineral exploration and resource estimation, which plays a significant role in the economic evaluation of mining projects. Currently available methods are based either on geometrical approaches or geostatistical techniques that often considers the grade as a regionalised variable. In this paper, we propose a grade estimation technique that combines multilayer feed-forward neural network (NN) and k-nearest neighbour (kNN) models to estimate the grade distribution within a mineral deposit. The models were created by using the available geological information (lithology and alteration) as well as sample locations (easting, northing, and altitude) obtained from the drill hole data. The proposed approach explicitly maintains pattern recognition over the geological features and the chemical composition (mineral grade) of the data. Prior to the estimation of grades, rock types and alterations were predicted at unsampled locations using the kNN algorithm. The presented case study demonstrates that the proposed approach can predict the grades on a test dataset with a mean absolute error (MAE) of $0.507$ and $R^2=0.528$, whereas the traditional model, which only uses the coordinates of sample points as an input, yielded an MAE value of $0.862$ and $R^2=0.112$. The proposed approach is promising and could be an alternative way to estimates grades in a similar modelling tasks.

Resources estimation is one of the critical tasks to evaluate the economic feasibility of a mineral deposit. Traditional prediction workflows, which often involve kriging and inverse distance weighting methods, may not always be suitable to estimate mineral grades for every type of mineralisation. In this study, we present a grade estimation workflow using gradient boosting-based machine learning methods, namely, XGBoost, LightGBM and CatBoost. The case study demonstrated that the three gradient descent-based models performed better than the OK method. XGBoost model demonstrated the best estimation performance with an $R^2$ of 0.728 accuracies, whereas traditional Ordinary Kriging (OK) model yielded 0.651 for $R^2$.