ABSTRACT

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 $R^2$.

摘要

资源估算是评价矿床经济可行性的关键任务之一。传统的预测工作流程通常涉及克里金法和反距离加权方法，可能并不总是适合估计每种矿化类型的矿物品位。在这项研究中，我们使用基于梯度提升的机器学习方法，即 XGBoost、LightGBM 和 CatBoost，提出了一个等级估计工作流程。案例研究表明，三个基于梯度下降的模型的性能优于 OK 方法。XGBoost 模型展示了最好的估计性能${\mathrm{电阻}}^2$ 0.728 的准确率，而传统的普通克里金 (OK) 模型产生了 0.651 ${\mathrm{电阻}}^2$.