ANN-Based Wheat Chlorophyll Density Estimation Using Canopy Hyperspectral Vegetation Indices

Abstract:

Canopy leaf Chlorophyll Density is a key index for evaluating crop potential photosynthetic efficiency and nutritional stress. Leaf Chlorophyll Density estimate using canopy hyperspectral vegetation indices provides a rapid and non-destructive method to evaluate yield predictions. A systematic comparison of two approaches to estimate Chlorophyll Density using 6 spectral vegetation indices (VIs) was presented in this study. In this study, the traditional statistical method based on power regression analyses was compared to the emerging computationally powerful techniques based on artificial neural network (ANN). The regression models of TCARI 、SAVI 、MSAVI and RDVIgreen were found to be more suitable for predicting Chlorophyll Density when only traditional statistical method was used especially TCARI and RDVI. ANN method was more appropriate to develop prediction models. The comparisons between these two methods were based on analysis of the statistic parameters. Results obtained using Root Mean Square Error (RMSE) for ANNs were significantly lower than the traditional method. From this analysis it is concluded that the neural network is more robust to train and estimate crop Chlorophyll Density from remote sensing data.

• Periodical: Key Engineering Materials (Volume 500)
• Pages: 243-249
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.500.243
• Online since: January 2012
• Authors: Da Cheng Wang, Luo Rui Sen, Ji Hua Wang, Cun Jun Li, Dong Yan Zhang, Yao Zhang, Yu Fei Li
• Keywords: Artificial Neural Network (ANN), Chlorophyll Density, Hyperspectral Vegetation Index, Mathematical Power Regression, Wheat

References

[1] Arco-Tejada, P.J., Miller, J.R., Mohammed, G.H., Noland, T.L., Sampson, P.H., 2002. Vegetation stress detection through chlorophyll a+b estimation and fluorescence effects on hyperspectral imagery. Journal of Environmental Quality 31 (5), 1433–1441.

DOI: 10.2134/jeq2002.1433

[2] Carter, G.A., Cibula, W.G., Miller, R.L., 1996. Narrow-band reflectance imagery compared with thermal imagery for early detection of plant stress. Journal of Plant Physiology 148 (5), 515-520.

DOI: 10.1016/s0176-1617(96)80070-8

[3] Miller J R, Hare E W, Wu J. Quantitative Characterization of the vegetation red edge reflectance model [J]. Int J Remote Sensing, 1990, 11 (10) : 1755-1773.

DOI: 10.1080/01431169008955128

[4] Plummer S E, North P R, Briggs SA. The angular vegetation index: an atmospherically resistance index for the second long track scanning radiometer (ATSR- 2) . Proceedings of the Sixth International Symposium of Physical Measurements and Signatures in Remote Sensing. Val d'Isere , France , (1994).

[5] YANG M h , LIU L y , Research on a Method to Retrieve Biophysical and Biochemical.

[6] Parameters of Wheat Canopy with Hyper spectral Remote Sensing [J ]. , 2002 , 31(4) : 3162321.

[7] LIU Wei-dong, XIANG Yue-qin, ZHENG Lan-fen, et al. Relationships between Rice LAI, CH. D and Hyperspectra Data[J], Journal of Remote Sensing, 2000, 4(4): 279-283.

[8] SONG Kai-shan; ZHANG Bai; WANG Zong-ming. Soybean LAI Estimation with in-situ Collected Hyperspectral Data Based on BP-Neural Networks [J ]. Scientia Agricultura Sinica, 2000, 4 (4): 2792 1145.

[9] WU Chang-shan, XIANG Yue-qin, ZHENG Lan-fen, et al. Estimating Chlorophyll Density of Crop Canopies by Using Hyperspectral Data [J]. Journal of Remote Sensing, 2000, 4(3): 228-231.

[10] Huang Wen-jiang, WANG Ji-hua, . Study on Grain Quality Effecting Factors and Monitoring Methods by Using Hyperspectral Data in Winter Wheat [J]. REMOTE SENSING TECHNOLOGY AND APPLICATION, 2004, 19(3): 143-148.

[11] WANG Zhi-jie, WANG Ji-hua, Huang Wen-jiang. Studies on the Nitrogen State of Leaf, Culm and Sheath at Different Layers in Canopy and Their Relationship with Grain Quality in Winter Whea[J]t. Scientia Agricultura Sinica(China). 2003, 36(12) : 1462-1468.

[12] Johnson L F, Hlavaka C A, Peterson D L. Multivariate analysis of aviris data for canopy, biochemical estimation along the Oregon transect[J]. Remote Sens. Environ ., 1994, 47: 216 - 230.

DOI: 10.1016/0034-4257(94)90157-0

[13] Maderia A C, Mendonca A, Ferreira ME et al. . Relationship between spectroradiometric and chlorophyll measurements in green beans Communication [J]. Soil Science and Plant Analysis, 2000, 31 (5 - 6) : 631 - 643.

DOI: 10.1080/00103620009370465

[14] Xue Hongli, Luo Hongwei , Cao Weixing. Research Progress on the Water and Nitrogen Detection Using Spectral Reflectance [J]. JOURNAL OF REMOTE SENSING , 2003, 7 (1) : 73 – 80.

[15] TIAN Yong-chaoZHU YanYAO XiaLIU Xiao-junCAO Wei-xing Non-destructive monitoring of crop nitrogen nutrition based on spectral information. CHINESE JOURNAL OF ECOLOGY [J]. 2007 26(9).

[16] Wang K, Shen Z Q, Wang R C. Effects of nitrogen nutrition on the spectral reflectance characteristics of rice leaf and canopy[J]. Journal of Zhejiang Agricultural University , 1998 , 24 (1) : 93 - 97.

[17] SUN Yan-xinWANG Ji-huaLI Bao-guo, Generalized Regression Neural Network Based on the Genetic Algorithm in Selection of Spectral Parameter of Winter Wheat Leave's Total Nitrogen.

[18] Huang Wen-jiang, WANG Ji-hua, . Correlation between grain quality indicators and spectral reflectance properties of wheat canopies by using hyperspectral data from winter wheat , [J]. TRANSACTIONS OF THE CHINESE SOCIETY OF AGRICULTURAL ENGINEERING  2004, 20(4): 203-207.

[19] WANG Xiu-zhengWANG Ren-chaoLi Yun-meiSHEN Zhang-quan . Study on red edge characteristics of rice spectral caused by nitrogen level [J]. JOURNAL OF ZHEJIANG UNIVERSITY , 2001 27 (3) : 301 - 306.

[20] Tang Yan-ling, Wang Ren-cao, Zhang Jinheng. Study on Determining Nitrogenous Levels of Barley by Hyperspectral and Chlorophyll Meter [J]. JOURNAL OF TRITICEAE CROPS, 2003, 23 (1) : 63 – 66.

[21] Huang Jingfeng, Wang Yuan, Wang Fumin, Liu Zhanyu  [J]. TRANSACTIONS OF THE CHINESE SOCIETY OF AGRICULTURAL ENGINEERING, 2006, 22(8): 22-26.

[22] SUN Yan-xinWANG Ji-huaLI Bao-guoLIU Liang-yunHUANG Wen-jiangZHAO Chun-jiang , Contrastive Analysis Based on Neural Network of Winter Wheat's Chlorophyll Concentration Inversion with Hyperspectral Data.

[23] REMOTE SENSING TECHNOLOGY AND APPLICATION, 2007, 4: 31-36 4.