Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Determination of Nitrogen Content in Rice Crop Using Multi-Spectral Imaging

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  Paper number  031132,  2003 ASAE Annual Meeting . (doi: 10.13031/2013.13741) @2003
Authors:   Cheng-Wei Huang, Chun-Chi Huang, Chih-Kai Yang, Te-Hui Wu, Yang-Zenq Tsai, Pa-Lung Miao
Keywords:   Multi-Spectral Image, Rice, Nitrogen Content, Precision Agriculture

In this study, the nitrogen content of rice plants were measured by remote sensing using multispectral imaging techniques. The multi-spectral imaging model using 4 band wavelengths at 555, 660, 680 and 780nm was successfully developed to predict the nitrogen content in rice (Oryza sativa L. cv. Tainung 67). The model gave results of r =0.84, SEC = 0.21, RSEC=12.7% for calibration and r = 0.77, SEP = 0.31, RSEP = 15.5% for prediction. This model was applied to predict nitrogen content in different variety of rice (Taiken 14) and gave results of r=0.72, SEP=0.29, RSEP=17.3%. The prediction results of Tainung 67 in different growth stage and year gave the results of r=0.70, SEP=0.35, RSEP=17.3%. The model exhibited the feasibility of wide applications to different rice varieties and growth years. The model was further applied to the analysis of the distribution of nitrogen content in rice plants in a large scale of paddy field by taking multi-images at 15m above the ground using a mobile lift. The information of crops nitrogen distribution could contribute to the development of a decision support system for a site-specific crop management in precision agriculture.

(Download PDF)    (Export to EndNotes)