RAN Zhi-yi ,XIAO Lu ,CUI Ning-bo ,ZHANG Zhi-liang ,CAI Huan-jie ,ZHANG Bao-zhong
China Rural Water and Hydropower. 2020, (2):
93-99.
Download PDF
(
)
Knowledge map
 
Save
Crop evapotranspiration (ET) is a key parameter of agricultural water management, the accurate estimation of ET is of great significance to the realization of precise irrigation management and the allocation of regional water resources. In order to effectively improve the prediction accuracy of summer maize ET in Northwest China, a model for estimating summer maize evapotranspiration in Northwest China is established based on generalized regression neural network (GRNN) by using summer maize crop index and meteorological factors from 2011 to 2013, and the results are compared with those of Shuttleworth-Wallace (S-W) physical model. The results show that, compared with the ET measured by large-scale transpirator in different periods of summer maize, the simulation effect of GRNN on ET in different growth stages and whole growth stages of summer maize is better. In the whole growth stages, the optimum simulation model of ET for summer maize is M12 (input T, n, LAI), MAE, NSE,R2,MRE, RRMSE and GPI ranking were 0.925 2 mm/d, 0.550 0, 0.553 6, 0.836 8, 0.430 7 and 4, respectively. The optimum simulation model of ET for summer maize from seedling to tasseling stage is MⅠ-14 (input fc, H), MAE、NSE、R2、MRE、RRMSE and GPI were 0.866 0 mm/d, 0.391 7, 0.425 2, 0.360 6, 0.399 0 and 2, respectively. The MAE、NSE、R2、MRE、RRMSE and GPI ranked were 0.5 933 mm/d, 0.753 7, 0.760 1, 0.229 9, 0.284 0 and 1 respectively for the optimal model MⅡ-9 (input n, T, RH, LAI) in tasseling to grouting stage, and the related parameters were 0.325 8 mm/d, 0.857 0, 0.885 2, 0.211 2, 0.215 5 and 2 for the optimal model MⅢ-11 (input RH, n, T) for the filling-harvesting period. At the same time, the simulation value of GRNN model is much more accurate than that of S-W model. Therefore, the evapotranspiration estimation model based on generalized regression neural network can be used to accurately simulate the evapotranspiration of Summer Maize in different growth stages in Northwest China with fewer input parameters.