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.
Key words
evapotranspiration simulation /
summer maize /
generalized regression neural network /
Shuttleworth-Wallace model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1]XU C Y, SINGH V P. Evaluation of three complementary relationship evapotranspiration models by water balance approach to estimate actual regional evapotranspiration in different climatic regions[J]. Journal of hydrology, 2005,308(1-4):105-121.
[2]BURBA G G, VERMA S B. Seasonal and interannual variability in evapotranspiration of native tallgrass prairie and cultivated wheat ecosystems[J]. Agricultural and forest meteorology, 2005,135(1-4):190-201.
[3]WANG S T, ZHU G F, XIA D S, et al. The characteristics of evapotranspiration and crop coefficients of an irrigated vineyard in arid Northwest China[J]. Agricultural water management, 2019,212:388-398.
[4]BORMANN H. Sensitivity analysis of 18 different potential evapotranspiration models to observed climatic change at German climate stations[J]. Climatic change, 2011,104(3-4):729-753.
[5]RANA G, KATERJI N. Measurement and estimation of actual evapotranspiration in the field under Mediterranean climate: a review[J]. European journal of agronomy, 2000,13(2-3):125-153.
[6]王 娟,王建林,刘家斌,等.基于Penman-Monteith模型的2个蒸散模型在夏玉米农田的参数修正及性能评价[J].应用生态学报,2017,28(6):1 917-1 924.
[7]冯禹,崔宁博,龚道枝,等.基于叶面积指数改进双作物系数法估算旱作玉米蒸散[J].农业工程学报,2016,32(9):90-98.
[8]AMAZIRH A, ER-RAKI S, CHEHBOUNI A, et al. Modified Penman–Monteith equation for monitoring evapotranspiration of wheat crop: Relationship between the surface resistance and remotely sensed stress index[J]. Biosystems engineering, 2017,164:68-84.
[9]TANG D H, FENG Y, GONG D Z, et al. Evaluation of artificial intelligence models for actual crop evapotranspiration modeling in mulched and non-mulched maize croplands[J]. Computers and electronics in agriculture, 2018,152:375-384.
[10]KUMAR D, ADAMOWSKI J, SURESH R, et al. Estimating evapotranspiration using an extreme learning machine model: case study in north Bihar, India[J]. Journal of irrigation and drainage engineering, 2016,142(9).
[11]SHUTTLEWORTH W J, WALLACE J S. Evaporation from sparse crops‐an energy combination theory[J]. Quarterly journal of the royal meteorological society, 1985,111(469):839-855.
[12]ZHOUM C, ISHIDAIRA H, HAPUARACHCHI H P, et al. Estimating potential evapotranspiration using Shuttleworth-Wallace model and NOAA-AVHRR NDVI data to feed a distributed hydrological model over the Mekong River basin[J]. Journal of hydrology, 2006,327(1-2):151-173.
[13]王小川,史峰,郁磊,等. MATLAB 神经网络43个案例分析[M]. 北京:北京航空航天大学出版社,2013:67-73.
[14]SPECHT D F. A general regression neural network[J]. IEEE transactions on neural networks, 1991,2(6):568-576.
[15]FAN J L, WANG X K, WU L F, et al. New combined models for estimating daily global solar radiation based on sunshine duration in humid regions: A case study in South China[J]. Energy conversion and management, 2018,156:618-625.
[16]梁文清. 冬小麦、夏玉米蒸发蒸腾及作物系数的研究[D]. 陕西杨凌：西北农林科技大学,2012.
[17]王子申. 基于作物模型的陕西关中地区冬小麦灌溉制度优化研究[D].陕西杨凌：西北农林科技大学,2016.
[18]KII. Generalized regression neural networks for evapotranspiration modelling[J]. Hydrological sciences journal, 2006,51(6):1 092-1 105.
PDF(224 KB)
鄂公网安备 42010602001274号 鄂ICP备14015464号-1