Automated prediction of phosphorus concentration in soils using reflectance spectroscopy and machine learning algorithms.

A method is presented for predicting total phosphorus concentration in soils from Santander de Quilichao, Colombia, using a UV-VIS V-750 Spectrophotometer and machine learning techniques. A total of 152 soil samples, prepared with varying proportions of PO fertilizer and soil, were analyzed, obtaining reflectance spectra in the 200 to 900 nm range with 3501 wavelengths. Additionally, 152 laboratory results of total phosphorus concentration were used to train the prediction model.

Dataset for the determination of phosphorus in soil through the analysis of hyperspectral images.

This article presents the capture protocol to acquire hyperspectral images, which can be used to quantify the concentration of total phosphorus in soil samples. 152 soil samples were prepared, and a hyperspectral cube made up of 145 images in the VIS-NIR bands, between 420 and 1000 nm, was obtained from each of them. The images obtained were taken with the Bayspec OCIF Series hyperspectral camera, in push-broom function, using a platform that includes an illumination system that offers a continuous spectrum in the range of interest.