Estimating Ore Grade Using Evolutionary Machine Learning Models

This book explores the capabilities of new machine learning models for predicting ore grade in mining engineering, presenting case studies and discussing uncertainty in ore grade modeling. It offers advanced and hybrid models for estimating ore grade and serves as a comprehensive handbook for mining engineers, modelers, and industrial managers.

Format: Hardback
Length: 101 pages
Publication date: 27 December 2022
Publisher: Springer Verlag, Singapore

This comprehensive book delves into the remarkable capabilities of new machine learning models in predicting ore grade in mining engineering. Through a series of case studies, it explores the effectiveness of these models in accurately estimating various variables, making them applicable across different scientific disciplines. The absence of robust models for estimating ore grade served as the driving force behind the preparation of this invaluable resource. Mining engineers can rely on this book to determine ore grade with remarkable precision. Moreover, it assists in identifying mineral-rich regions for exploration and exploitation, thereby reducing exploration costs.

The author discusses innovative concepts in mining engineering, including the challenges associated with modeling uncertainty in ore grade. Ensemble models are presented as a solution to this problem, offering a reliable approach to estimate ore grade. This book provides readers with the knowledge and skills necessary to construct advanced machine learning models for estimating ore grade, surpassing traditional methods such as kriging. It serves as a comprehensive handbook for ore grade estimation, catering to industrial managers, modelers, and professionals across various fields.

The book addresses the previous shortcomings in the modeling process of ore grades, encompassing mining engineering, soft computing models, and artificial intelligence. By presenting advanced optimizers for training machine learning models, it empowers modelers to develop robust and efficient systems for predicting ore grade. This book is a valuable asset for anyone seeking to enhance their understanding and expertise in this field.

Weight: 348g
Dimension: 235 x 155 (mm)
ISBN-13: 9789811981050
Edition number: 1st ed. 2023