PDF Download

[1]LOU Zhongqiu,Li zhen.Different Simplified Algorithm Models Simulate Reference Crop Evapotranspiration in Dujiangyan Irrigation District[J].Research of Soil and Water Conservation,2019,26(05):272-277,286.

Copy

Different Simplified Algorithm Models Simulate Reference Crop Evapotranspiration in Dujiangyan Irrigation District

Research of Soil and Water Conservation[ISSN 1005-3409/CN 61-1272/P] Volume: 26 Number of periods: 2019 05 Page number: 272-277,286 Column: Public date: 2019-09-06

Title:: Different Simplified Algorithm Models Simulate Reference Crop Evapotranspiration in Dujiangyan Irrigation District

Author(s):: LOU Zhongqiu^1,2, Li zhen¹; 1. Sichuan Water Conservancy Vocational College, Dujiangyan, Sichuan 611800, China;
2. State Key Laboratory of Hydraulics and Mountain River Engineering & College of Water Resource and Hydropower, Sichuan University, Chengdu 610065, China

Keywords:: reference crop evapotranspiration; radiation; the extreme learning machine; the generalized regression neural network; the Penman-Monteith model

CLC:: S161.4

DOI:: -

Abstract:: In order to find a simplified calculation model for reference crop evapotranspiration (ET₀) in Dujiangyan Irrigation District, based on daily weather data from 1961 to 2017 in Chengdu, Dujiangyan, Leshan, Suining and Ya’an sites near the irrigation district, we calculated the daily ET₀ data of the Penman-Monteith (PM) model, the extreme learning machine (ELM) model, the generalized regression neural network (GRNN) model, the Priestley-Taylor (PT) model, the Makkink (MK) model, and the Ritchie (RC) model. The relative root mean square error (RMSE), the decision coefficient (R²) and the model efficiency coefficient (E_ns) were used as the evaluation index system to compare the calculation accuracy of different models. The results showed that the GRNN model and the ELM model displayed the higher computational accuracy and consistency; the R² of ELM model ranged from 0.852 4 to 0.911 0, and the RMSE ranged form 0.363 to 0.413 mm/d, the E_ns ranged from 0.856 to 0.903; the R² of GRNN model ranged from 0.835 7 to 0.886 3, and the RMSE were 0.366~0.497 mm/d, the E_ns were 0.832~0.879. It is known that radiation is a key factor in the calculation of ET₀ by comparing the simulation accuracy of the two models before and after the input radiation. In summary, the ELM model has higher calculation accuracy and can be used as the ET₀ standard calculation model in the case of missing meteorological data in Dujiangyan Irrigation District.

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, 2005,308:105-121.
[2] 黄垚,王景雷,孙景生,等.作物蒸散不同时空尺度模型及尺度转换方法研究进展[J].中国农业通报,2013,29(21):23-26.
[3] 卢晓鹏,段顺琼,马显莹,等.单双作物系数法计算玉米需水量的对比研究[J].节水灌溉,2012(11):18-21.
[4] Allen R G, Pereira L S, Raes D, et al. Crop evapotranspirationguidelines for computing crop water requirements[M]. Rome:Food and Agriculture Organization of United Nation, 1998.
[5] 冯禹,崔宁博,龚道枝.机器学习算法和Hargreaves模型在四川盆地ET₀计算中的比较[J].中国农业气象,2016,37(4):415-421.
[6] 王升,陈洪松,聂云鹏,等.基于基因表达式编程算法的参考作物腾发量模拟计算[J].农业机械学报,2015,46(4):106-112.
[7] Samani Z. Estimating solar radiation and evapotranspiration using minimum climatological data[J]. Journal of Irrigation and Drainage, 2000,126(4):265-267.
[8] 贾悦,崔宁博,魏新平,等.气候变化与灌溉对都江堰灌区参考作物蒸散量影响研究[J].四川大学学报:工程科学版,2016,48(S1):69-79.
[9] 李晨,崔宁博,冯禹,等.四川省不同区域参考作物蒸散量计算方法的适用性评价[J].农业工程学报,2016,32(4):127-134.
[10] Feng Y, Cui N, Zhao L, et al. Comparison of ELM, GANN, WNN and empirical models for estimating reference evapotranspiration in humid region of Southwest China[J]. Journal of Hydrology, 2016,536:376-383.
[11] 张薇,霍树义,贾悦.机器学习模型在河北省参考作物蒸散量计算中的比较[J].节水灌溉,2018(4):50-53,58.
[12] 李翊.都江堰灌区空间信息技术应用现状与需求分析[J].中国农村水利水电,2015(12):30-34.
[13] 贾悦,崔宁博,魏新平,等.基于反距离权重法的长江流域参考作物蒸散量算法适用性评价[J].农业工程学报,2016,32(6):130-138.
[14] Priestley C H B, Taylor R J. On the assessment of surface heat flux and evapotranspiration using large-scale parameters[J]. Monthly Weather Review, 1972,100(2):81-92.
[15] Makkink G F. Testing the Penman Formula by means of lysimeters[J]. Instit. Water Engineers, 1957,11:277-288.
[16] Hoffman G J, Howell T A. Management of Farm Irrigation Systems[M]//Management of farm irrigation systems. American Society of Agricultural Engineers, 1990.
[17] 冯禹,崔宁博,龚道枝,等.基于极限学习机的参考作物蒸散量预测模型[J].农业工程学报,2015,31(S1):153-160.
[18] 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.
[19] 李菲菲,饶良懿,吕琨珑,等. Priestley-Taylor模型参数修正及在蒸散发估算中的应用[J].浙江农林大学学报,2013,30(5):748-754.
[20] 符娜,宋孝玉,夏露,等.云南省不同生态水文分区参考作物蒸散量算法适用性评价[J].农业机械学报,2017,48(5):208-217.
[21] 刘晓英,林而达,刘培军. Priestley-Taylor与Penman法计算参照作物腾发量的结果比较[J].农业工程学报,2003,19(1):32-36.
[22] 左德鹏,徐宗学,程磊,等.基于辐射的潜在蒸散量估算方法适用性分析[J].干旱区地理,2011,34(4):565-573.
[23] 邓艾东,赵力,包永强.粒子群优化小波神经网络用于碰摩声发射源定位[J].中国电机工程学报,2009,29(32):83-87.
[24] Huang G B, Zhu Q Y, Siew C H. Extreme learning machine:theory and applications[J]. Neurocomputing, 2006,70(1/2/3):489-501.
[25] 王少福,张金磊,赵仕俊,等.广义回归神经网络的改进及在预测控制中的应用[J].微电子学与计算机,2009,26(6):32-35.

Similar References:

Memo

Last Update: 1900-01-01