Quantification of Kaolinite and Halloysite Using Machine Learning from FTIR, XRF, and Brightness Data

Abstract

Quantification of halloysite and kaolinite in clay deposits from X-ray diffraction (XRD) commonly requires extensive sample preparation to differentiate the two phyllosilicates. When assessing hundreds of samples for mineral resource estimations, XRD analyses may become unfeasible due to time and expense. Fourier transform infrared (FTIR) analysis is a fast and cost-effective method to discriminate between kaolinite and halloysite; however, few efforts have been made to use this technique for quantified analysis of these minerals. In this study, we trained machine- and deep-learning models on XRD data to predict the abundance of kaolinite and halloysite from FTIR, chemical composition, and brightness data. The case study is from the Cloud Nine kaolinite–halloysite deposit, Noombenberry Project, Western Australia. The residual clay deposit is hosted in the saprolitic and transition zone of the weathering profile above the basement granite on the southwestern portion of the Archean Yilgarn Craton. Compared with XRD quantification, the predicted models have an R2 of 0.97 for kaolinite and 0.96 for halloysite, demonstrating an excellent fit. Based on these results, we demonstrate that our methodology provides a cost-effective alternative to XRD to quantify kaolinite and halloysite abundances.

Understanding Iron Impurities in Australian Kaolin and Their Effect on Acid and Heat Activation Processes of Clay

“…The aim of this study was not to delineate between halloysite and kaolinite as both are polymorphs of the kaolin group. It is technically difficult to quantify them separately without a combination of tools, although machine learning technology has proven to be useful . However, based on Du Plessis et al and an independent consulting report on the Cloud Nine deposit, a mineral composition specification was provided (Table ).…”

“…It is technically difficult to quantify them separately without a combination of tools, although machine learning technology has proven to be useful. 9 However, based on Du Plessis et al 9 and an independent consulting report on the Cloud Nine deposit, 14 a mineral composition specification was provided ( Table 1 ). We received a database of clay mineral abundance for 100 drill hole profiles showing variations in mineral abundance.…”

“…Western Australia clay mineral deposits offer a wide range of kaolin minerals with various iron oxide content along with other impurities, including feldspar, mica, quartz, smectite, and illite. Recently, kaolin of varying quality was found in the Cloud Nine kaolinite–halloysite deposit, Noombenberry, Western Australia . However, understanding only mineral compositions of this clay are not sufficient to determine the economic potential of it.…”

“…Geological deposits of kaolin are widespread across the world, with new exploration being commissioned. − The study of new sites is important for evaluating end-use and to understand how the product can be improved relative to its mineralogy and mineral properties. Western Australia clay mineral deposits offer a wide range of kaolin minerals with various iron oxide content along with other impurities, including feldspar, mica, quartz, smectite, and illite.…”

“…Recently, kaolin of varying quality was found in the Cloud Nine kaolinite–halloysite deposit, Noombenberry, Western Australia. 9 However, understanding only mineral compositions of this clay are not sufficient to determine the economic potential of it. Large-scale deposits like Noombenberry, Western Australia showed diverse kaolin types, including tubular halloysite and platy kaolinite as well as their iron-bearing impurities.…”