Feasibility of using successive projections algorithm in spectral monitoring of rice leaves nitrogen contents

Liu Mingbo; Tang Yanlin; Li Xiaoli; Lou Jia

5 segments moving average, baseline correction, area normalization, and multiplicative scatter correction (MSC) was used to preprocess Visible-NIR reflective spectrum of rice leaf. Successive projection algorithm (SPA) was used in the selecting of effective wavelengths. Multiple linear regression (MLR) models were built based on spectral indexes of RVI, NDVI and effective wavelengths selected by SPA. Principal components regression (PCR) models and Partial least squares regression (PLS) models were built based on all wavelengths in the spectrum. Nitrogen contents of rice leaves were predicted by these models. From comparison, It was found that the predictive validity of models based on SPA effective wavelengths were obviously better than models based on spectral indexes of RVI and NDVI, and slightly worse than PCR and PLS models based on all wavelengths in the spectrum. Models based on MSC preprocessed spectrum and SPA effective wavelengths has the predictive validity of r=0.7943, RMSE=0.4558. It is feasible to use successive projections algorithm in spectral monitoring of rice leaves nitrogen contents.

1. College of Sciences,Guizhou University,Guiyang 550025,China

Received Date: 2013-08-10

Rev Recd Date: 2013-09-25

Publish Date: 2014-04-25

Key words:

Abstract: 5 segments moving average, baseline correction, area normalization, and multiplicative scatter correction (MSC) was used to preprocess Visible-NIR reflective spectrum of rice leaf. Successive projection algorithm (SPA) was used in the selecting of effective wavelengths. Multiple linear regression (MLR) models were built based on spectral indexes of RVI, NDVI and effective wavelengths selected by SPA. Principal components regression (PCR) models and Partial least squares regression (PLS) models were built based on all wavelengths in the spectrum. Nitrogen contents of rice leaves were predicted by these models. From comparison, It was found that the predictive validity of models based on SPA effective wavelengths were obviously better than models based on spectral indexes of RVI and NDVI, and slightly worse than PCR and PLS models based on all wavelengths in the spectrum. Models based on MSC preprocessed spectrum and SPA effective wavelengths has the predictive validity of r=0.7943, RMSE=0.4558. It is feasible to use successive projections algorithm in spectral monitoring of rice leaves nitrogen contents.

HTML

Reference (21)

[1]
[2]	Wang Ke, Shen Zhangquan, Wang Renchao. Vegetation nutrient condition and spectral feature [J]. Remote Sensing for Land Resources, 1999, 39: 9-14. (in Chinese) 王珂, 沈掌泉, 王人潮. 植物营养胁迫与光谱特性[J]. 国土资源遥感, 1999, 39: 9-14.
[3]	Liu Fei, Zhang Fan, Fang Hui, et al. Application of successive projections algorithm to nondestructive determination of total amino acids in oilseed rape leaves [J]. Spectroscopy and Spectral Analysis, 2009, 29 (11): 3079-3083. (in Chinese) 刘飞, 张帆, 方慧, 等. 连续投影算法在油菜叶片氨基酸总量无损检测中的应用[J]. 光谱学与光谱分析, 2009, 29 (11): 3079-3083.
[4]
[5]	Wu D, He Y, Shi J H, et al. Exploring near and midinfrared spectroscopy to predict trace iron and zinc contents in powdered milk [J]. J Agric Food Chem, 2009, 57: 1697-1704.
[6]
[7]
[8]	Goudarzi N, Goodarzi M. Application of successive projections algorithm (SPA) as a variable selection in a QSPR study to predict the octanol/water partition coefficients (KOW) of some halogenated organic compounds [J]. Anal Methods, 2010, 2: 758-764.
[9]
[10]	Arajo M C U, Saldanha T C B, Galvo R K H, et al. The successive projections algorithm for variable selection in spectroscopic multicomponent [J]. Chemom Intell Lab Syst, 2001, 57: 65-73.
[11]	Galvo R K H, Arajo M C U, Fragoso W D, et al. A variable elimination method to improve the parsimony of MLR models using the successive projections algorithm [J]. Chemom Intell Lab Syst, 2008, 92: 83-91.
[12]
[13]
[14]	Lou Jia, Tang Yanlin, Cai Shaohong, et al. Correlation between transmittance spectra and nitrogen content for rice[J]. Chinese Agricultural Science Bulletin, 2009, 25 (24): 544-548. (in Chinese) 楼佳, 唐延林, 蔡绍洪, 等. 水稻透射光谱与氮含量的相关性研究[J]. 中国农学通报, 2009, 25 (24): 544-548.
[15]
[16]	Lou Jia. Nitrogen nutrition monitoring and diagnosis of rice with spectral analysis method [D]. Guiyang: Guizhou University, 2010. (in Chinese) 楼佳. 用光谱法研究水稻的氮素营养状况[D]. 贵阳: 贵州大学, 2010.
[17]	Liu F, He Y, Sun G M. Determination of protein content of auricularia auricular using near infrared spectroscopy combined with linear and nonlinear calibrations [J]. J Agric Food Chem, 2009, 57: 4520-4527.
[18]
[19]	Li Yingxue, Zhu Yan, Tian Yongchao, et al. Relationship of grain protein content and relevant quality traits to canopy reflectance spectra in wheat [J]. Scientia Agricultura Sinica, 2005, 38(7): 1332-1338. (in Chinese) 李映雪, 朱艳, 田永超, 等. 小麦冠层反射光谱与籽粒蛋白质含量及相关品质指标的定量关系[J]. 中国农业科学, 2005, 38(7): 1332-1338.
[20]
[21]	Yan Chunyan, Niu Zheng, Wang Jihua, et al. The assessment of spectral indices applied in chlorophyll content retrieval and a modified crop canopy chlorophyll content retrieval model [J]. Journal of Remote Sensing, 2005, 9(6): 742-750. (in Chinese) 颜春燕, 牛铮, 王纪华, 等. 光谱指数用于叶绿素含量提取的评价及一种改进的农作物冠层叶绿素含量提取模型[J]. 遥感学报, 2005, 9(6): 742-750.

Feasibility of using successive projections algorithm in spectral monitoring of rice leaves nitrogen contents

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views