Application of BP Neural Network in Predicting Winter Wheat Yield Based on Thermography Technology
HU Zhen-fang1, ZHANG Lu-da2, WANG Yu-xuan3, Shamaila Z3, ZENG Ai-jun2, SONG Jian-li2, LIU Ya-jia2, Wolfram S3, Joachim M3, HE Xiong-kui1,2*
1. College of Engineering, China Agricultural University, Beijing 100083, China 2. College of Science, China Agricultural University, Beijing 100193, China 3. Institute of Agricultural Engineering (440) University Hohenheim, Stuttgart 70599, Germany
摘要: 通过使用红外热像仪技术获得冬小麦冠层不同温度值,计算得到冬小麦主要需水阶段水分胁迫指标ICWSI(infrared crop water stress index)。并根据此数据,使用一次灌溉周期中3个时段不同的ICWSI的平均值作为输入因子,相应实测冬小麦产量作为输出因子,建立了BP神经网络模型对冬小麦的产量进行预测,本文采用三层BP神经网络,其拓扑结构为3-5-1,数据归一化处理后收敛性能增强。预测结果显示,平均相对误差最大只有3.42%;为了证实这一方法的优越性,同时建立了基于ICWSI和冬小麦产量关系的非线性函数的预测模型,预测结果与实际产量值进行比较,平均相对误差最大达到了18.87%。两种预测方法得到的不同预测结果表明,将红外热像仪技术与BP神经网络预测方法相结合,可以成功用来预测冬小麦产量,比使用非线性函数预测的效果更好,精度更高,可靠性更强,可以用于实际生产需要。
关键词:红外热像仪;ICWSI;BP神经网络;冬小麦产量
Abstract:Using a thermal camera to obtain canopy temperatures for winter wheat, an infrared crop water stress index (ICWSI) was calculated in the main water-requirement stage. The performance of a BP neural network was tested with ICWSI values for three different periods in one irrigation circle as independent input factors and observed winter wheat yield after harvest as the output. The topology of the neural network was 3-5-1, and after data normalization, convergence performance was enhanced. Results showed that the maximum relative error was only 3.42%. To confirm the superiority of this method, a common nonlinear regression model was also built to compare the predictions with ICWSI values and the observed yield of winter wheat, but the maximum relative error of this model was higher (18.87%). Comparison between these two mathematical methods shows that the approach of combining thermal camera technology with a BP neural network prediction model, which is more precise for nonlinear prediction, was sufficiently better than other models to predict the winter wheat yield successfully and accurate enough to meet production requirements.
胡振方1,张录达2,王珏璇3, Shamaila Z3, 曾爱君2,宋坚利2,刘亚佳2,Wolfram S3, Joachim M3, 何雄奎1,2*. BP神经网络在使用红外热像仪技术预测冬小麦产量中的应用[J]. 光谱学与光谱分析, 2013, 33(06): 1587-1592.
HU Zhen-fang1, ZHANG Lu-da2, WANG Yu-xuan3, Shamaila Z3, ZENG Ai-jun2, SONG Jian-li2, LIU Ya-jia2, Wolfram S3, Joachim M3, HE Xiong-kui1,2*. Application of BP Neural Network in Predicting Winter Wheat Yield Based on Thermography Technology. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(06): 1587-1592.
[1] Jones H G. Plant, Cell & Enviroment, 1999, 22(9): 1043. [2] Padhi J,Misra R K,Payero J O. Field Crops Research,2012,126: 44. [3] Braunworth W S Jr,Mack H J. Journal of the American Society for Horticultural Science,1989, 114(4):542. [4] Erdem Y, Erdem T, Orta A H, et al. Journal of Central Europen Agriculture, 2005, 6(4): 449. [5] Orta A H, Erdem Yesim, Erdem Tolga. Scientia Horticulturae,2003,98:121. [6] Irmark S, Haman D Z, Bastug R. Agro. J.,2000, 1221. [7] LIU Zengjin, Li Baoping, Li Yuanhua, et al. Transactions of the CSAE, 2004, 20(4): 58. [8] Wu Zhongdong, Wang Quanjiu. Transactions of the CSAM, 2010, 41(9): 36. [9] Wang Shufen, Zhang Xiying, Pei Dong. Transactions of the CSAE, 2006,22(2): 27. [10] Huang Wenjiang, Yuan Hongchun, Wang Jihua, et al. Computer and Agriculture,2000,10: 21. [11] Zhao Zhenguo, Liu Li,Xu Xinjian. Yello River,2007,29(9):59. [12] Chen Xiangjun, Wang Chunning, Chen Shengtan. Beijing: International Industry Press, 1995. [13] Lv Shuran, Lv Shujin. Procedia Engineering, 2011,26:257. [14] Idso S B, Jackson R D, Pinter P J, et al. Agricultural Meteorlogy, 1981,24: 45. [15] Idso S B. Agricultural Meteorlogy, 1982, 27: 59. [16] IlkkaLenonen, Hamlyn G Jones. Journal of Experimental Botany, 2004, 55: 1423. [17] Ali Abdullah Alderfasi,David C Nielsen. Agricultural Water Management, 2001, 47:69. [18] Yuan G,Luo Y,Sun X,et al. Agricultural Water Management, 2004, 64:29. [19] Payero J O, Irmak S. Irrigation Science, 2006, 25:21. [20] Chen Bo, Ouyang Zhu. Transactions of the Chinese Society of Agricultural Engineering, 2010, 26(4): 81.