Tomato Evapotranspiration Prediction Based on the NLPCA-RBF Neural Networks

doi:10.11924/j.issn.1000-6850.2013-1858

Abstract

Abstract: Evapotranspiration (ET) is one of the main components of the hydrologic cycle. Accurate estimation of ET is essential for studies such as water management and irrigation system design. In this study, a hybrid model that integrated Nonlinear Principal Component Analysis (NLPCA) method with the radial basis function (RBF) neural network (NLPCA-RBF) was used for estimating Tomato ET. On the premise that not only the integrity of the meteorological information can be guaranteed but the correlation among different factors can be eliminated, NLPCA was applied to simplify the seven main meteorological factors which related to the ET into three principal components .Then used these components as input and the measured ET as output target, therefore, the network was created and verified by parts of the data were not used in design of the network. By comparing with RBF neural network, the results showed that NLPCA-RBF network model can well reflected the relationship between meteorological factors and evapotranspiration and got more accurate result.

References

[1] 杨凡,齐永青,张玉翠,等.大孔径闪烁仪与涡度相关系统对灌溉农田蒸散量的对比观测[J].中国生态农业学报,2011,19(5):1067- 1071.
[2] Abedi-Koupai J, Amiri M J, Eslamian S S. Comparison of Artificial Neural Network and Physically Based Models for Estimating of Reference Evapotranspiration in Greenhouse[J].Australian Journal of Basic and Applied Sciences,2009,3(3):2528-2535.
[3] Ditthakit P, Chinnarasri C. Estimation of Pan Evaporation Coefficient using Neuro-Genetic Approach[J].American Journal of Environmental Sciences,2011,7(4):397-401.
[4] Hankerson B, Kjaersgaard J, Hay C. Estimation of Evapotranspiration from Fields with and without Cover Crops Using Remote Sensing and in situ Methods[J].Remote Sensing, 2012,4(12):3796-3812.
[5] 王永东,李生宇,徐新文,等.Hargreaves 公式在塔克拉玛干沙漠腹地的适用性[J].中国沙漠,2013,33(2):367-371.
[6] 张淑杰,班显秀,纪瑞鹏,等.农田蒸散量模型构建及蒸散状况分析[J].中国农学通报,2006,22(10):454-458.
[7] Laaboudi A, Mouhouche B, Draoui B. Neural network approach to reference evapotranspiration modeling from limited climatic data in arid regions[J].International Journal of Biometeorology,2012,56(5): 831-841.
[8] Khoshhal J, Mokarram M. Model for Prediction of Evapotranspiration Using MLP Neural Network[J].International Journal of Environmental Sciences, 2012,3(3):1000-1009.
[9] 张志政,娇亚涛,李伟.基于 GA-BP神经网络的作物参考腾发量预测[J].农机化研究,2011,33(1):61-63.
[10] 徐俊增,彭世彰,张瑞美,等.基于气象预报的参考作物蒸发蒸腾量的神经网络预测模型[J].水利学报,2006,37(3):376-379.
[11] 陈博,欧阳竹.基于BP神经网络的冬小麦耗水预测[J].农业工程学报,2010,26(4):81-85.
[12] 张丽,吴金亮,杨国范.基于BP神经网络的东港灌区作物需水量预测研究[J].水土保持研究,2012,19(6):207-210.
[13] 刘婧然,马英杰,王喆,等.基于 RBF 神经网络与 BP 神经网络的核桃作物需水量预测[J].节水灌溉,2013(3):16-19.
[14] 郑重,马富裕,李江全.基于BP神经网络的农田蒸散量预报模型[J].水利学报,2008,39(2):230-234.
[15] 徐璐璐,孙来君,刘明亮,等.基于SPA-RBF神经网络的小麦蛋白质含量无损检测[J].中国农学通报,2013,29(9):208-211.
[16] 欧剑锋,程吉林.基于主成分 BP人工神经网络的参考作物腾发量预测[J].灌溉排水学报,2008,27(2):55-58.
[17] 赵杰辉,葛少云,刘自发.基于主成分分析的径向基函数神经网络在电力系统负荷预测中的应用[J].电网技术,2004,28(5):35-37.
[18] 朱顺泉,徐国祥.中国上市公司财务状况的非线性主成分分析研究[J].经济数学,2002,19(4):69-72.
[19] 史峰,王小川,郁磊,等.MATLAB 神经网络 30 个案例分析[M].北京:北京航空航天大学出版社,2010:65-72.
[20] Deshmukh S C, Senthilnath J, Dixit R M, et al. Comparison of Radial Basis Function Neural Network and Response Surface Methodology for Predicting Performance of Biofilter Treating Toluene[J].Journal of Software Engineering and Applications,2012,5 (8):595-603.