Abstract

Supervised analysis using spectral data requires a well-informed characterisation of the response variables and abundant spectral data points. The presented hyperspectral dataset comes from fve sets of geometallurgical samples, each characterised by diferent methods. To provide the spectral data, all mineral samples were scanned with SPECIM VNIR and SWIR hyperspectral cameras. For each subset the following data are provided 1) hyperspectral refectance images in the VNIR spectral range (400–1000nm wavelength); 2) hyperspectral refectance images in the SWIR spectral range (900–2500nm wavelength); 3) hyperspectral refectance images in the VNIR-SWIR range (merged to SWIR spatial resolution); 4) RGB images constructed from hyperspectral data using a Bilateral Filter based sensor fusion method; 5) response variables representing mineral sample characterisation results, provided as training and validation data. This dataset is intended for use in general regression and classifcation research and experiments. All subsets were validated using machine learning models with satisfactory results.