Copper Ore Grade Prediction using Machine Learning Techniques in a Copper Deposit

The objective of this research work to employ machine learning techniques including Multilayer Perceptron Artificial Neural Networks (ANN-MLP), Random Forests (RFs), Extreme Gradient Boosting (XGBoost), and Support Vector Regression (SVR) to predict copper ore grades in a copper deposit located in Peru. The models were developed using ۵۶۵۴ composites containing available geological information (rock type), as well as the locations of the samples (east, north, and altitude) and secondary ore grade (Mo) obtained from drilling wells. The data was divided into ۱۰% (۵۶۵ composites) for testing, ۱۰% (۵۶۵ composites) for validation, and ۸۰% (۴۵۲۳ composites) for training. The evaluation metrics included SSE (Sum of Squared Errors), RMSE (Root Mean Squared Error), NMSE (Normalized Mean Squared Error), and R&sup۲; (Coefficient of Determination). The XGBoost model could predict the ore grade with an SSE of ۱۵.۶۷, RMSE = ۰.۱۷, NMSE = ۰.۳۴, and R&sup۲; = ۰.۶۶, the RFs model with an SSE of ۱۶.۴۰, RMSE = ۰.۱۷, NMSE = ۰.۳۶, and R&sup۲; = ۰.۶۵, the SVR model with an SSE of ۱۹.۹۴, RMSE = ۰.۱۹, NMSE = ۰.۴۳, and R&sup۲; = ۰.۵۷, and the ANN-MLP model with an SSE = ۲۱.۰۰, RMSE = ۰.۱۹, NMSE = ۰.۴۶, and R&sup۲; = ۰.۵۵. In conclusion, the XGBoost model was the most effective in predicting copper ore grades.

کلیدواژه ها:

Multilayer Perceptron Artificial Neural Network ، Random Forests ، Extreme Gradient Boosting ، Support Vector Regression