2 February 2006 Prediction of soil macronutrients content using near infrared spectroscopy
Author Affiliations +
Proceedings Volume 6031, ICO20: Remote Sensing and Infrared Devices and Systems; 603117 (2006) https://doi.org/10.1117/12.668046
Event: ICO20:Optical Devices and Instruments, 2005, Changchun, China
Near-infrared spectroscopy is a rapid and nondestructive technique that has the ability to analyze many constituents at the same time and has been used to quantify various soil properties. The objective of this study was to analyze NIR spectroscopy potential to estimate N, P, K, OM and pH content in a loamy mixed soil. 165 soil samples were taken from the field, 135 samples spectra were used during the calibration and validation stage, and 30 sample spectra were used for the prediction of N, P, K, OM and pH content. Principal Component Analysis/Partial Least Square (PCA/PLS) was used as multivariate analysis technique to correlate wavelength information with each constituent concentration. The r between measured and predicted values of N, OM and pH was 0.93, 0.93 and 0.91, as well as SEP, 3.28, 0.06 and 0.07, respectively, demonstrated that NIRS method has potential to predict accurately these constituents in soil. Unfortunately, statistics between measured and predicted P and K with r, 0.47 and 0.68, and SEP, 33.70 and 26.54, respectively, demonstrated a poorly for P and a less successfully K prediction. The result also shows that NIR could be a good tool to be combined with precision farming application.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yong He, Yong He, Haiyan Song, Haiyan Song, Annia García, Annia García, Antihus Hernández, Antihus Hernández, "Prediction of soil macronutrients content using near infrared spectroscopy", Proc. SPIE 6031, ICO20: Remote Sensing and Infrared Devices and Systems, 603117 (2 February 2006); doi: 10.1117/12.668046; https://doi.org/10.1117/12.668046

Back to Top