Comparison of different multivariate calibrations and ensemble methods for estimating selected soil properties with vis-NIR reflectance spectroscopy

Sustainable soil management requires a correct assessment of soil chemical and physical properties. Historically, this has been gained through conventionallaboratory analyses, which are considered costly and time-consuming, particularlywhen a large number of soil samples need to be analysed. An alternative, faster andless expensive, approach is based on the use of reflectance spectroscopy in the visNIR domain. This approach implies the calibration of predictive models that relatethe spectral reflectance to soil properties. The goodness of the models can be particularly influenced by the multivariate methods used. In this article, we compare theperformance of different multivariate and statistical ensemble methods for estimatingsome basic soil properties, such as sand, silt, clay, and organic carbon in the specificpedo-environmental conditions of an important agricultural area in southern Italy.