The Nitrogen Content Prediction Model of Cold Region Rice Canopy at the Tillering Stage Based on Hyperspectral Imaging

DOI

10.2991/icadme-17.2017.58How to use a DOI?

Keywords

Rice canopy, Hyper-spectrum, Nitrogen content, Tillering stage, Regression analysis

Abstract

In order to detect the nitrogen content of the rice canopy fast and nondestructively in the cold region, the hyperspectral technique was used to capture the rice canopy spectrum information at the tillering stage. After vegetation index was constructed by the characteristic waveband of high correlation, the linear regression prediction model and index combination prediction model was verified and analyzed. The result shows that the reflectance of rice canopy of tillering stage has significant differences in visible light band (492nm ~ 622nm) and near infrared band (greater than 770nm), and there is high correlation between rice canopy nitrogen content and 554nm, 736nm, 733nm light bands. The accuracy and stability of the linear regression prediction model is better with SI 773 , DSI(773,554) as the variables, while the RC2 is 0.771, 0.724 and the RP2 is 0.789, 0.773 respectively. The two vegetation indices combination model constructed by DSI(773,554), NDSI(773,554) and the five vegetation indices combination model constructed by DSI(773,554), DSI(773,736), RSI(736,554), RSI(773,554), NDSI(736,554) performed better than linear regression prediction model, while RC2 is 0.773, 0.795 and RP2 is 0.801, 0.784.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yitong Liu
AU  - Yuzhu Song
AU  - Shuwen Wang
AU  - Yu Zhao
PY  - 2017/07
DA  - 2017/07
TI  - The Nitrogen Content Prediction Model of Cold Region Rice Canopy at the Tillering Stage Based on Hyperspectral Imaging
BT  - Proceedings of the 2017 7th International Conference on Advanced Design and Manufacturing Engineering (ICADME 2017)
PB  - Atlantis Press
SP  - 297
EP  - 302
SN  - 2352-5401
UR  - https://doi.org/10.2991/icadme-17.2017.58
DO  - 10.2991/icadme-17.2017.58
ID  - Liu2017/07
ER  -