Deep-XFCT: Deep learning 3D-mineral liberation analysis with micro X-ray fluorescence and computed tomography

The rapid development of X-ray micro-computed tomography (μCT) opens new opportunities for 3D analysis of particle and grain-size characterisation, determination of particle densities and shape factors, estimation of mineral associations and liberation, and locking. Current practices in mineral liberation analysis are based on 2D representations leading to systematic errors in the extrapolation to volumetric properties. New quantitative methods based on tomographic data are therefore urgently required for the characterisation of mineral deposits, mineral processing, characterisation of tailings, rock typing, stratigraphic refinement, reservoir characterisation for applications in the resource industry, environmental and material sciences. To date, no simple non-destructive method exists for 3D mineral liberation analysis. We present a new development based on combining μCT with micro-X-ray fluorescence (μXRF) using deep learning. We demonstrate successful semi-automated multi-modal analysis of a crystalline magmatic rock where the new technique overcomes the difficult task of differentiating feldspar from quartz in μCT data set. The approach is universal and can be extended to any multi-modal and multi-instrument analysis for further refinement. We conclude that the combination of μCT and μXRF already provides a new opportunity for robust 3D mineral liberation analysis in both field and laboratory applications.