Estimating Ore Grade Using Evolutionary Machine Learning Models

Mohammad Ehtearm is a Researcher in the field of artificial intelligence. He has a Ph.D. in civil engineering. His research interests generally lie in the areas application of remote sensing in water resources, water, energy, and food nexus, extreme hydrological events, river engineering, remote sensing in water resources, dam and hydropower operation, geotechnical engineering, mining engineering, artificial intelligence, and remote sensing in mining engineering. Zohreh Sheikh Khozani is a Scientific Researcher in the field of civil engineering and mining engineering. The scope of her current research is covering hydraulic structures, hydrology, water resources engineering, environmental engineering, and the implementation of data analytics, geotechnical engineering, mining engineering, and artificial intelligence models. Saeed Soltani-Mohammadi is Associate Professor at Department of Mining Engineering, University of Kashan, Iran. He holds a PhD on mining engineering from the Amirkabir University of technology in 2009. His research spans application of artificial intelligence and optimization methods in geosciences and mining problems. He developed many soft computing models based on practical applications for mining engineering. Maliheh Abbaszadeh is Assistant Professor at Department of Mining Engineering, University of Kashan, Iran. She holds a Ph.D. in mining engineering from the Amirkabir University of technology in 2014. She developed her teaching activity in the areas of geochemical exploration, remote sensing and machine learning algorithms. Her primary research interest is application of machine learning algorithms in exploratory data analysis.

Explains the importance of ore grade estimation.- Reviews machine learning models for ore grade estimation.- Explains the structure of different kinds of machine learning models.- Explains different training algorithms and optimization algorithms. This chapter also explains the structure of evolutionary machine learning models.- Explains the Bayesian model averaging and multilayer perceptron networks for estimating AL2O3 grade in a mine.- Explains the structure of inclusive multiple models and optimized radial basis function neural networks for estimating Sio2 grade in a mine.- Explains the application of hybrid kriging and extreme learning machine models for estimating copper ore grade in a mine.- Explains the application of optimized group machine data handling, support vector machines, and Adaptive neuro-fuzzy interface systems for estimating iron ore grade in mines.- Presents the conclusion, general comments, and suggestions for the next books.