Prediction Of Multiple Soil Fertility Parameters Using Visnir Spectroscopy And Pxrf Spectrometry

Visible and near-infrared (VisNIR) spectroscopy and portable X-ray fluorescence (PXRF) spectrometry are successful in estimating soil attributes. However, it is still necessary to investigate their performance in estimating soil fertility properties. In this study, for the soil fertility properties of soil organic C (SOC), available N, total P, available P, total K, and available K, the performance of using VisNIR and PXRF individually and combined, three data fusion methods (concatenation, model fusion and model averaging), and two modeling methods was evaluated. The results showed that combining VisNIR and PXRF did not substantially improve the prediction accuracy of SOC, total P, total K and available K. Using VisNIR alone could predict them well, achieving the best prediction in total K (R-2 = .90, ratio of performance to interquartile distance [RPIQ] = 5.08, and residual prediction deviation [RPD] = 3.13), followed by SOC (R-2 = .77, RPIQ = 2.05, and RPD = 2.10), total P (R-2 = .63, RPIQ = 2.35, and RPD = 1.64), and available K (R-2 = .53, RPIQ = 2.04, and RPD = 1.41). Both available N and available P were poorly estimated by all the methods proposed in this study. Although PXRF alone could predict total P, total K, and available K with acceptable accuracy, it did not perform well on SOC (R-2 < .32, RPIQ < 1.16, and RPD < 1.19). Hence, for the precision application of organic and NPK fertilizers, VisNIR is supposed to be the optimal way to rapidly obtain soil information.