Estimating Canopy Nitrogen Content of Rice Using Hyperspectral Reflectance Combined with SG-FD-CARS-ELM in Cold Region
International Journal of Industrial and Manufacturing Systems Engineering
Volume 3, Issue 4, July 2018, Pages: 25-34
Received: Nov. 15, 2018; Accepted: Dec. 4, 2018; Published: Dec. 28, 2018
Views 389      Downloads 44
Authors
Wang Shuwen, College of Information Engineering, Lingnan Normal University, Zhanjiang, China; College of Electrical and Information Engineering, Northeast Agricultural University, Harbin, China
Xiu Cheng, College of Electrical and Information Engineering, Northeast Agricultural University, Harbin, China
Zhao Qinghe, College of Electrical and Information Engineering, Northeast Agricultural University, Harbin, China
Li Xiaowei, College of Electrical and Information Engineering, Northeast Agricultural University, Harbin, China
Zhang Yan, College of Electrical and Information Engineering, Northeast Agricultural University, Harbin, China
A Mani, College of Electrical and Information Engineering, Northeast Agricultural University, Harbin, China
Wang Runtao, College of Information Engineering, Lingnan Normal University, Zhanjiang, China
Article Tools
Follow on us
Abstract
In this study, visible and near infrared hyperspectral imaging technique was used to predict canopy leaf nitrogen content (CLNC) of rice in cold region. Canopy hyperspectral images of rice were acquired at tillering, jointing and heading stage, respectively. Original spectra was extracted using ENVI5.0 software, and leaf nitrogen content was obtained by chemical analysis method. 5 pre-processing methods of savitzky-golay smoothing (SG), multiplicative scatter correction (MSC), standard normal variate (SNV), first derivative (FD) and second derivative (SD) were used to eliminate unexpected noise. After comparing the performance of PLSR models based on spectra of full wavelengths after pre-processing, SG combined with FD had the best performance for eliminating the noise interference and improving the performance of models. In order to further simplify and enhance the models, 3 variable selection methods of successive projections algorithm (SPA), uninformative variable elimination (UVE) and competitive adaptive reweighted sampling (CARS) were used to select the characteristic wavelengths, and partial least square regression (PLSR) and extreme learning machine (ELM) were used to establish prediction models. After comparing the performance of PLSR models and ELM models, CARS could effectively select the wavelengths that had strong information and were not sensitive to external disturbance factors, and the nonlinear ELM model was more suitable for predicting CLNC of rice in cold region, the specific values of RC2 and RP2 of ELM models based on CARS were 0.906 and 0.888 for tillering stage, 0.903 and 0.892 for jointing stage, and 0.894, 0.887 for heading stage, respectively. The results of this study could provide a reference for quantitative analysis of nitrogen content of rice using hyperspectral technology.
Keywords
Hyperspectral Imaging, Rice, Canopy Nitrogen Content, Pre-processing, Wavelength Selection
To cite this article
Wang Shuwen, Xiu Cheng, Zhao Qinghe, Li Xiaowei, Zhang Yan, A Mani, Wang Runtao, Estimating Canopy Nitrogen Content of Rice Using Hyperspectral Reflectance Combined with SG-FD-CARS-ELM in Cold Region, International Journal of Industrial and Manufacturing Systems Engineering. Vol. 3, No. 4, 2018, pp. 25-34. doi: 10.11648/j.ijimse.20180304.11
Copyright
Copyright © 2018 Authors retain the copyright of this article.
This article is an open access article distributed under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
References
[1]
Wu Q, Xia G M, Chen T T, et al. 2016. Impacts of nitrogen and zeolite managements on yield and physicochemical properties of rice grain. International Journal of Agricultural and Biological Engineering, 9 (5): 93-100.
[2]
He Y, Zhao C J, Wu D, et al. 2010. Fast detection technique and sensor instruments for crop-environment information: A review. Scientia Sinica (Informationis), 40 (S): 1-20.
[3]
Wang S W, Song Y Z, Zhang C L, et al. 2017. Hyperspectral estimation model for predicting canopy nitrogen content of rice in cold region of Northeast China. Journal of Northeast Agricultural University, 48 (4): 79-88.
[4]
Yu F H, Xu T Y, Cao Y L, et al. 2016. Models for estimating the leaf NDVI of japonica rice on a canopy scale by combining canopy NDVI and multisource environmental data in Northeast China. International Journal of Agricultural and Biological Engineering, 9 (5): 132-142.
[5]
Xue X Y, Tu K, Qin W C, et al. 2014. Drift and deposition of ultra-low altitude and low volume application in paddy field. International Journal of Agricultural and Biological Engineering, 7 (4): 23-28.
[6]
Wang R H, Song X Y, Li Z H, et al. 2014. Estimation of winter wheat nitrogen nutrition index using hyperspectral remote sensing. Transactions of the Chinese Society of Agricultural Engineering, 30 (19): 191-187.
[7]
Sun J, Cong S L, Mao H P, et al. 2017. CARS-ABC-SVR model for predicting leaf moisture of leaf-used lettuce based on hyperspectral. Transactions of the Chinese Society of Agricultural Engineering, 33 (5): 178-184.
[8]
Tian Y C, Gu K J, Chu X, et al. 2014. Comparison of different hyperspectral vegetation indices for canopy leaf nitrogen concentration estimation in rice. Plant and Soil, 376 (1-2): 193-209.
[9]
Chu X, Guo Y J, He J Y, et al. 2014. Comparison of different hyperspectral vegetation indices for estimating canopy leaf nitrogen accumulation in rice. Agronomy Journal, 106 (5): 1911-1920.
[10]
Yu K, Li F, Gnyp M L, et al. 2013. Remotely detecting canopy nitrogen concentration and uptake of paddy rice in the Northeast China Plain. ISPRS Journal of Photogrammetry and Remote Sensing, 78: 102-115.
[11]
Qin Z F, Chang Q R, Xie B N, et al. 2016. Rice leaf nitrogen content estimation based on hyperspectral imagery of UAV in Yellow River diversion irrigation district. Transactions of the Chinese Society of Agricultural Engineering, 32 (23): 77-85.
[12]
Yu F H, Xu T Y, Du W, et al. 2017. Radiative transfer models (RTMs) for field phenotyping inversion of rice based on UAV hyperspectral remote sensing. International Journal of Agricultural and Biological Engineering, 10 (4): 150-157.
[13]
Li X Q, Liu X N, Liu M L, et al. 2014. Random forest algorithm and regional applications of spectral inversion model for estimating canopy nitrogen concentration in rice. Journal of Remote Sensing, 18 (4): 923-945.
[14]
Bi Y M, Yuan K L, Xiao W Q, et al. 2016. A local pre-processing method for near-infrared spectra, combined with spectral segmentation and standard normal variate transformation. Analytica Chimica Acta, 909: 30–40.
[15]
Jia B B, Yoon S C, Zhuang H, et al. 2017. Prediction of pH of fresh chicken breast fillets by VNIR hyperspectral imaging. Journal of Food Engineering, 208: 57-65.
[16]
Helland I S, Nas T, Isaksson T. 1995. Related versions of the multiplicative scatter correction method for preprocessing spectroscopic data. Chemometrics and Intelligent Laboratory Systems, 29 (2): 233-241.
[17]
Shen F, Yang D T, Ying Y B, et al. 2012. Discrimination between Shaoxing wines and other Chinese rice wines by near-infrared spectroscopy and chemometrics. Food and Bioprocess Technology, 5 (2): 786-795.
[18]
Wu D, Sun D W. 2013. Application of visible and near infrared hyperspectral imaging for non-invasively measuring distribution of water-holding capacity in salmon flesh. Talanta, 116: 266-276.
[19]
He H J, Sun D W, Wu D. 2014. Rapid and real-time prediction of lactic acid bacteria (LAB) in farmed salmon flesh using near-infrared (NIR) hyperspectral imaging combined with chemometric analysis. Food Research International, 62: 476–483.
[20]
Wu D, Sun D W, He Y. 2014. Novel non-invasive distribution measurement of texture profile analysis (TPA) in salmon fillet by using visible and near infrared hyperspectral imaging. Food Chemistry, 145: 417-426.
[21]
Zhu N, Lin M H, Nie Y T, et al. 2016. Study on the quantitative measurement of firmness distribution maps at the pixel level inside peach pulp. Computers and Electronics in Agriculture, 130: 48-56.
[22]
Zou X B, Zhao J W, Malcolm J W P, et al. 2010. Variables selection methods in near-infrared spectroscopy. Analytica Chimica Acta, 667 (1-2): 14-32.
[23]
Araújo M C U, Saldanha T C B, Galvão R K H, et al. 2001. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemometrics and Intelligent Laboratory Systems, 57 (2): 65-73.
[24]
Cai W S, Li Y K, Shao X G. 2008. A variable selection method based on uninformative variable elimination for multivariable calibration of near-infrared spectra. Chemometrics and Intelligent Laboratory Systems, 90 (2): 188-194.
[25]
Li H D, Liang Y Z, Xu Q S, et al. 2009. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. Analytica Chimica Acta, 648 (1): 77-84.
[26]
Huang L X, Zhou Y B, Meng L W, et al. 2017. Comparison of different CCD detectors and chemometrics for predicting total anthocyanin content and antioxidant activity of mulberry fruit using visible and near infrared hyperspectral imaging technique. Food Chemistry, 224: 1-10.
[27]
Iqbal A, Sun D W, Allen P. 2013. Prediction of moisture, color and pH in cooked, pre-sliced turkey hams by NIR hyperspectral imaging system. Journal of Food Engineering, 117 (1): 42-51.
[28]
Meng R F, Zhong J J, Zhang L F, et al. 2012. Ultrasonic concentration measurement of citrus pectin aqueous solutions using PC and PLS regression. International Journal of Agricultural and Biological Engineering, 5 (2): 76-81.
[29]
Liu Y, Xie H, Chen Y H, et al. 2016. Neighborhood mutual information and its application on hyperspectral band selection for classification. Chemometrics and Intelligent Laboratory Systems, 157: 140-151.
[30]
Wu D, He Y. 2014. Potential of spectroscopic techniques and chemometric analysis for rapid measurement of docosahexaenoic acid and eicosapentaenoic acid in algal oil. Food Chemistry, 158: 93-100.
ADDRESS
Science Publishing Group
1 Rockefeller Plaza,
10th and 11th Floors,
New York, NY 10020
U.S.A.
Tel: (001)347-983-5186