Abstract
Chile is one of the major producers of copper in the world, and as such is responsible for 1.7 million tons of tailings per day. While the most commonly used deposit to store this type of mining waste is historically tailings sand dams, the mining industry has over the last two decades been inclined toward thickened tailings dams (TTD) because of their advantages in water resource recovery, lower environmental impact, and better physical and chemical stability over conventional deposits. Within the geotechnical area, one key requirement of TDD, is the need to monitor moisture content (w%) during operation, which is today mostly performed in situ – via conventional geotechnical or simple visual means by TTD operators – or off site, via remote sensing. In this work, an intelligent system is proposed that allows estimation of different classes of in-situ states and w% in TTD using Machine learning algorithms based on Artificial Neural Networks (ANN), Support Vector Machine (SVM) and Random Forest (RF). The results show an accuracy of between 94% and 97% in the classification task of the Dry, Semisolid, Plastic and Saturated classes, and between 0.356 and 0.378 of the MAE metric in the regression task, which is sufficient to estimate the w% with ML methods.
Highlights
While the Chilean mining industry produced 5600 MT of copper in 2019 – one of the major sources worldwide [1] – it is expected to reach 7.04 million tons of copper by 2030, peaking in 2027 at 7.33 million tons [2]
The application of Artificial Intelligence (AI) to geotechnical engineering has progressed since the 90s, and has explored techniques such as Artificial Neural Networks (ANN), Linear Regression (LR) Analysis, Support Vector Machine (SVM), Random Forest (RF) and M5 model trees (M5P) [13], [23]–[25]
Following the same methodology presented in article [5], [6] [7], we obtain the correlations between the images (RGB and NIR) and the in-situ w% of the experimental thickened tailings dams (TTD) using the normalized reflection intensity with respect to the dry soil corrected by the spectral power
Summary
While the Chilean mining industry produced 5600 MT of copper in 2019 – one of the major sources worldwide [1] – it is expected to reach 7.04 million tons of copper by 2030, peaking in 2027 at 7.33 million tons [2]. Satellite image analysis is increasingly becoming a technology at scale in the follow-up and monitoring of tailings deposits, for the control of growth, deformations, and movement of the clear water lagoon To this end, in reporting on combinations of remote sensing methodology, [5]–[7] evaluated the use of satellite and hyperspectral images (captured by unmanned aerial vehicle UAV) in correlating the reflection of light on the surface of a TTD and its surface w% as determined from field and laboratory tests. The results obtained in terms of the intensity of reflection normalized to dry soil was shown to have high correlation, suggesting a precise and cost-efficient technology for monitoring surface moisture in TTDs [6] Such approaches have yet to be extensively implemented in monitoring tailings water content. This work presents ML techniques as a potential multidimensional image analysis alternative to more efficiently discern surface soil moisture calibrated to the needs of the current and future Chilean mining industry
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call