基于可见光光谱和BP人工神经网络的冬小麦生物量估算研究

崔日鲜; 刘亚东; 付金东

doi:doi:10.3964/j.issn.1000-0593(2015)09-2596-06

光谱学与光谱分析, 2015, 35 (9): 2596, 网络出版: 2016-01-25

基于可见光光谱和BP人工神经网络的冬小麦生物量估算研究

Estimation of Winter Wheat Biomass Using Visible Spectral and BP Based Artificial Neural Networks

论文大纲

崔日鲜 ^1,*刘亚东 ¹付金东 ²

作者单位

¹ 青岛农业大学农学与植物保护学院, 山东省旱作农业技术重点实验室, 山东青岛266109

² 中国农业科学院作物科学研究所, 北京100081

摘要

建立基于冬小麦冠层图像分析获取的冠层覆盖度和色彩指数的地上部生物量估算模型, 以促进作物冠层图像分析技术和BP神经网络技术在冬小麦长势无损监测中的应用。六个施氮水平的田间试验条件下, 在冬小麦拔节期, 分四次采集冬小麦冠层图像, 同步进行破坏性取样, 测定冬小麦地上部生物量; 分析了通过图像分析软件(利用微软Visual Basic软件开发)获取的冠层覆盖度和10种色彩指数与冬小麦地上部生物量的相关关系, 以逐步回归和BP神经网络方法建立了冬小麦地上部生物量估算模型。结果表明, 冬小麦地上部生物量与冠层覆盖度、饱和度和红光亮度值呈显著相关, 其中, 与冠层覆盖度间的相关性最强, 且除亮度外, 冠层覆盖度、色彩指数与地上部生物量间呈非线性相关。通过BP神经网络方法构建的模型相对于逐步回归模型, 显著提高了冬小麦地上部生物量估算精度, 均方根误差(RMSE)、相对均方根误差(RRMSE)更小, 决定系数(R2)更大。

Abstract

The objective of this study was to evaluate the feasibility of using color digital image analysis and back propagation (BP) based artificial neural networks (ANN) method to estimate above ground biomass at the canopy level of winter wheat field. Digital color images of winter wheat canopies grown under six levels of nitrogen treatments were taken with a digital camera for four times during the elongation stage and at the same time wheat plants were sampled to measure above ground biomass. Canopy cover (CC) and 10 color indices were calculated from winter wheat canopy images by using image analysis program (developed in Microsoft Visual Basic). Correlation analysis was carried out to identify the relationship between CC, 10 color indices and winter wheat above ground biomass. Stepwise multiple linear regression and BP based ANN methods were used to establish the models to estimate winter wheat above ground biomass. The results showed that CC, and two color indices had a significant correlation with above ground biomass. CC revealed the highest correlation with winter wheat above ground biomass. Stepwise multiple linear regression model constituting CC and color indices of NDI and b, and BP based ANN model with four variables (CC, g, b and NDI) for input was constructed to estimate winter wheat above ground biomass. The validation results indicate that the model using BP based ANN method has a better performance with higher R2 (0.903) and lower RMSE (61.706) and RRMSE (18.876) in comparation with the stepwise regression model.

参考文献

[1] YANG Bang-jie, PEI Zhi-yuan(杨邦杰, 裴志远). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 1999, 15(3): 214.

[2] LIANG Dong, GUAN Qing-song, HUANG Wen-jiang, et al(梁栋, 管青松, 黄文江, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2013, 29(7): 117.

[3] LI Jun-ling, ZHANG Hong, CAO Shu-chao(李军玲, 张弘, 曹淑超). J Maize. Sci.(玉米科学), 2013, 21(3): 149.

[4] Houborg R, Anderson M, Daughtry C. Remote Sensing of Environment, 2009, 113(1): 259.

[5] HUANG Chun-yan, WANG Deng-wei, CAO Lian-pu, et al(黄春燕, 王登伟, 曹连莆, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2007, 23(3): 131.

[6] ZHUANG Dong-ying, LI Wei-guo, WU Li-quan(庄东英, 李卫国, 武立权). Journal of Arid Land Resources and Environment(干旱区资源与环境), 2013, 27(10): 158.

[7] Nguyean H T, Lee B W. European Journal of Agronomy, 2006, 24(4): 349.

[8] WU Bing-fang, ZHANG Feng, LIU Cheng-lin, et al(吴炳方, 张峰, 刘成林, 等). Journal of Remote Sensing(遥感学报), 2004, 8(6): 498.

[9] Hunt Jr, E R Daughtry C S T McMurtrey, et al. In: Rober, P C, Rust R H, Larson W E (Eds.). Proceedings of the Sixth International Conference on Precision Agriculture and Other Precision Resources Management, ASA-CSSA-SSSA, Madison, Wl.

[10] Pan G, Li F, Sun G. 2007 IEEE International Geoscience and Remote Sensing Symposium, 2007. 797.

[11] Pagola M, Oritiz R, Irigoyen I, et al. Computers and Electronics in Agriculture, 2009, 65(2): 213.

[12] Behrens T, Diepenbrock W. Journal of Agronomy and Crop Science, 2006, 192(4): 295.

[13] Jia L, Chen X, Zhang F, et al. Journal of Plant Nutrition, 2004, 27(3): 441.

[14] WANG Yuan, WANG De-jian, ZHANG Gang, et al(王远, 王德建, 张刚, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2012, 28(17): 131.

[15] WANG Juan, LEI Yong-wen, ZHANG Yong-shuai, et al(王娟, 雷咏雯, 张永帅, 等). Chinese Journal of Eco-Agriculture(中国生态农业学报), 2008, 16(1): 145.

[16] Li Y, Chen D, Walker C N, et al. Field Crop Research, 2010, 118(3): 221.

[17] Lee K J, Lee B. W. European Journal of Agronomy, 2013, 48: 57.

[18] FU Yuan-yuan, WANG Ji-hua, YANG Gui-jun, et al(付元元, 王纪华, 杨贵军, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2013, 33(5): 1315.

[19] SONG Kai-shan, ZHANG Bai, WANG Zong-ming, et al(宋开山, 张柏, 王宗明, 等). Scientia Agricultura Sinica(中国农业科学), 2006, 39(6): 1138.

[20] XIA Tian, WU Wen-bin, ZHOU Qing-bo, et al(夏天, 吴文斌, 周清波, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2013, 29(3): 139.

[21] Rafael C, Gonzalez, Richard E Woods(冈萨雷斯, 伍兹). Digital Image Processing(数字图像处理). Beijing: Publishing House of Electronics Industry(北京: 电子工业出版社), 2011.

[22] Mao Wenhua, Wang Yiming, Wang Yueqing. Paper Number 031004, 2003 ASAE Annual Meeting. ASABE, St, Joseph, MI, USA, 2003.

[23] TIAN Yan, PENG Fu-yuan(田岩, 彭复员). Digital Image Processing and Analysis(数字图像处理与分析). Wuhan: Huazhong University of Science & Technology Press(武汉: 华中科技大学出版社), 2009. 140.

崔日鲜, 刘亚东, 付金东. 基于可见光光谱和BP人工神经网络的冬小麦生物量估算研究[J]. 光谱学与光谱分析, 2015, 35(9): 2596. CUI Ri-xian, LIU Ya-dong, FU Jin-dong. Estimation of Winter Wheat Biomass Using Visible Spectral and BP Based Artificial Neural Networks[J]. Spectroscopy and Spectral Analysis, 2015, 35(9): 2596.

基于可见光光谱和BP人工神经网络的冬小麦生物量估算研究

关于本站 Cookie 的使用提示

全站搜索

基于可见光光谱和BP人工神经网络的冬小麦生物量估算研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索