Exploring the relation between production factors, ore grades, and life of mine for forecasting mining capital cost through a novel cascade forward neural network-based salp swarm optimization model

• Published in: Resources policy Vol. 74; p. 102300
• Main Authors: Zheng, Xiaolei, Nguyen, Hoang, Bui, Xuan-Nam
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.12.2021; Elsevier Science Ltd
• Subjects: Accuracy; Algorithms; Artificial neural networks; Capital costs; Cascade feedforward neural network; Classification; Economic forecasting; Forecasting; Life of mine; Mathematical models; Mining; Mining capital cost; Mining industry; Networks; Neural networks; Open pit mining; Optimization; Optimization models; Ore grades; Parameters; Production; Production factors; Regression analysis; Root-mean-square errors; Salp swarm optimization; Sensitivity analysis; Support vector machines; Cascade feedforward neural network; Salp swarm optimization; Production factors; Ore grades; Life of mine; Mining capital cost
• ISSN: 0301-4207; 1873-7641
• DOI: 10.1016/j.resourpol.2021.102300

This paper aims at exploring the relationship between production factors, ore grades, and life of mine for forecasting mining capital cost (MCC) for open pit mining projects. Accordingly, the relationship between annual mine and mill production (MineAP, MillAP), stripping ratio (SR), reserve mean grade (RMG), the life of mine (LOM), and MCC of 80 open pit mining projects were investigated and thoroughly evaluated. The dataset was then divided into two sections, with 56 observations used to develop the forecast models. The remaining 24 observations were used to test the accuracy of the developed models. Subsequently, the cascade feedforward neural network (CFNN) was developed to forecast MCC based on the influential parameters. In order to improve the accuracy of the CFNN model, the salp swarm optimization (SalpSO) algorithm was applied to train the CFNN model and optimize the weights of the model, called the SalpSO-CFNN model. The benchmark models which were developed in the previous studies, such as support vector machine (SVM), classification and regression tree (CART), and multiple layers perceptron (MLP) neural network, were also developed in this study to compare with the proposed SalpSO-CFNN model in terms of MCC forecast. The results revealed that production factors, ore grades, and LOM are closely related to MCC, and they are statistically significant. The forecast results also indicated that the proposed novel SalpSO-CFNN model provided a good accuracy with a mean absolute error (MAE) of 179.567, root-mean-squared error (RMSE) of 248.401, and determination coefficient (R2) of 0.980. This result is higher by 18% compared with the CART model and 2–6% compared with the remaining forecast models. A sensitivity analysis also indicated that MineAP, MillAP are the most influential parameters on the forecast of MCC, and they should be specially taken into account when forecasting MCC of open pit mining projects. •The relationships between production factors, ore grades, life of mine, and mining capital cost were explored.•CFNN model was designed and developed for forecasting mining capital cost.•Salp swarm optimization was applied to optimize and improve the accuracy of the CFNN model.•The hybrid SalpSO-CFNN model was proposed to forecast MCC with high accuracy.•A comprehensive comparison of the SalpSO-CFNN, CFNN, MLP, SVM and CART models was performed.