机器学习算法和Hargreaves模型在四川盆地ET0计算中的比较

doi:10.3969/j.issn.1000-6362.2016.04.005

摘要/Abstract

摘要：

以四川盆地中部遂宁气象站2001-2010年逐日温度资料和大气顶层辐射（Ra）为输入参数，以FAO-56 Penman-Monteith（PM）模型计算的参考作物蒸散量（ET0）为标准，分别利用广义回归神经网络（GRNN）和小波神经网络（WNN）两种机器学习算法建立ET0模拟模型，并对GRNN、WNN和Hargreaves（HS1）与两种改进的Hargreaves（HS2和HS3）模型的ET0模拟效果进行对比分析，利用2011-2014年数据对各模型模拟精度进行验证，分析仅有温度资料时不同模型在四川盆地的适用性。结果表明：GRNN模型和WNN模型均具有较强的适用性，GRNN模型均方根误差（RMSE）、模型效率系数（Ens）和决定系数（R2）分别为0.395mm×d-1、0.924和0.902，WNN模型分别为0.401mm×d-1、0.911和0.901，且两种模型计算精度均高于HS1（1.05mm×d-1、0.885和0.334）、HS2（0.652mm×d-1、0.892和0.736）和HS3（0.550mm×d-1、0.881和0.812）模型。模型适用性验证进一步表明，GRNN和WNN模型在四川盆地西部和东部也具有较好的适用性，在输入参数中引入Ra能提高模型的模拟精度。因此，GRNN和WNN可以作为气象资料缺失条件下四川盆地ET0计算的推荐模型，且GRNN计算精度高于WNN，可优先选用。

关键词: 参考作物蒸散量, 温度资料, FAO-56 Penman-Monteith模型, 机器学习算法, Hargreaves模型

Abstract:

Reference evapotranspiration (ET0) is an essential component of agricultural water management, accurate estimation of ET0 is vital in irrigation scheduling. This study investigated the applicability of two machine learning algorithms, the generalized regression neural networks (GRNN) and wavelet neural networks (WNN), in modeling ET0 only with temperature data at Suining meteorological station, central Sichuan basin. The performances of GRNN and WNN models were compared with the empirical Hargreaves (HS1) and two calibrated Hargreaves (HS2, HS3) models. From the results, the root mean square error (RMSE), model efficiency (Ens) and coefficient of determination(R2) were 0.395mm×d-1, 0.924 and 0.902 for GRNN model, 0.401mm×d-1, 0.911 and 0.901 for WNN model, respectively. The performances of GRNN and WNN model were much better than HS1, HS2 and HS3 model. A further performances evaluation of GRNN and WNN model was conducted, which manifested the better applicability of GRNN and WNN models in western and eastern Sichuan basin.

Key words: Reference evapotranspiration, Temperature data, FAO-56 Penman-Monteith model, Machine learning algorithm, Hargreaves model

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(04): 415-421.

FENG Yu, CUI Ning-bo, GONG Dao-zhi. Comparison of Machine Learning Algorithms and Hargreaves Model for Reference Evapotranspiration Estimation in Sichuan Basin[J]. Chinese Journal of Agrometeorology, 2016, 37(04): 415-421.

参考文献

[1]冯禹,崔宁博,魏新平,等.川中丘陵区参考作物蒸散量时空变化特征与成因分析[J].农业工程学报,2014 30(14):78-86.

Feng Y,Cui N B,Wei X P,et al.Temporal-spatial distribution characteristics and causes analysis of reference crop evapotranspiration in hilly area of central Sichuan[J]. Transactions of the CSAE,2014,30(14):78-86.(in Chinese)

[2]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.

Wang S,Chen H S,Nie Y P,et al.Simulation of evapotranspiration based on gene-expression programming method[J].Transactions of the Chinese Society of Agricultural Machinery,2015,46(4):106-112.(in Chinese)

[3]Samani Z.Estimating solar radiation and evapotranspiration using minimum climatological data[J].Journal of Irrigation and Drainage,2000,126(4):265-267.

[4]徐俊增,彭世彰,丁加丽,等.基于蒸渗仪实测数据的日参考作物蒸发腾发量计算方法评价[J].水利学报,2010,41(12): 1497-1505.

Xu J Z,Peng S Z,Ding J L,et al.Evaluation of methods for estimating daily reference crop evapotranspiration based on lysimeter grass experiments[J].Journal of Hydraulic Engineering,2010,41(12):1497-1505.(in Chinese)

[5]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(增1):153-160.

Feng Y,Cui N B,Gong D Z,et al.Prediction model of reference crop evapotranspiration based on extreme learning machine[J].Transactions of the CSAE,2015,31(Supp.1): 153-160.(in Chinese)

[6]Hargreaves G H,Allen R G.History and evaluation of Hargreaves evapotranspiration equation[J].Journal of Irrigation and Drainage Engineering,2003,129(1):53-63.

[7]Almorox J,Quej V H,Marti P.Global performance ranking of temperature-based approaches for evapotranspiration estimation considering Köppen climate classes[J].Journal of Hydrology,2015,528: 514-522.

[8]Allen R G,Pereiral L S,Raes D,et al.Crop evapotranspiration: guidelines for computing crop water requirements[M]. Rome:FAO Irrigation and Drainage Paper 56,1998.

[9]胡庆芳,杨大文,王银堂,等.Hargreaves 公式的全局校正及适用性评价[J].水科学进展,2011,22(2): 160-167.

Hu Q F,Yang D W,Wang Y T,et al.Global calibration of Hargreaves equation and its applicability in china[J]. Advances in Water Science,2011,22(2):160-167.(in Chinese)

[10]李晨,崔宁博,魏新平,等.改进Hargreaves模型估算川中丘陵区参考作物蒸散量[J].农业工程学报,2015, 31(11): 129-135.

Li C,Cui N B,Wei X P,et al.Improvement of Hargreaves method for reference evapotranspiration in hilly area of central Sichuan Basin[J].Transactions of the CSAE,2015, 31(11):129-135.(in Chinese)

[11]Tabari H,Kisi O,Ezani A,et al.SVM,ANFIS,regression and climate based models for reference evapotranspiration modeling using limited climatic data in a semi-arid highland environment[J].Journal of Hydrology,2012,444:78-89.

[12]冯禹,王守光,崔宁博,等.基于遗传算法优化神经网络的参考作物蒸散量预测模型[J].资源科学,2014,36(12) 2624-2630.

Feng Y,Wang S G,Cui N B,et al.Artificial neural networks optimized by genetic algorithms for modeling reference evapotranspiration in Hilly Area in Central Sichuan[J]. Resources Science,2014,36(12):2624-2630. (in Chinese)

[13]Abdullah S S,Maleka M A,Abdullah N S,et al.Extreme learning machines:a new approach for prediction of reference evapotranspiration[J].Journal of Hydrology,2015, 527:184-195.

[14]Shiri J,Kisi O,Landeras G,et al.Daily reference evapotranspiration modeling by using genetic programming approach in the Basque Country(Northern Spain)[J].Journal of Hydrology,2012,414/415:302-316.

[15]Kisi O.Applicability of Mamdani and Sugeno fuzzy genetic approaches for modeling reference evapotranspiration[J]. Journal of Hydrology,2013,504:160-170.

[16]张玉芳,王锐婷,陈东东,等.利用水分盈亏指数评估四川盆地玉米生育期干旱状况[J].中国农业气象,2011, 32(4): 615-620.

Zhang Y F,Wang R T,Chen D D,et al.Evaluation on drought at maize growth stage in Sichuan basin on water budget index[J].Chinese Journal of Agrometeorology,2011,32(4): 615-620.(in Chinese)

[17]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.

Wang X C,Shi F,Yu L,et al.43 case analysis of neural network in MATLAB[M].Beijing:Beijing University of Aeronautics and Astronautics Press,2013.(in Chinese)

[18]彭琦,张茹,谢和平,等.基于AE时间序列的岩爆预测模型[J].岩土力学,2009,30(5):1436-1440.

Peng Q,Zhang R,Xie H P,et al.Prediction model for rockburst based on acoustic emission time series[J].Rock and Soil Mechanics,2009,30(5):1436-1440.(in Chinese)

[19]Hargreaves G H,Allen R G.History and evaluation of Hargreaves evapotranspiration equation[J].Journal of Irrigation and Drainage Engineering,2003,129(1):53-63.

[20]王保国,刘淑艳,钱耕,等.一种小波神经网络与遗传算法结合的优化方法[J].航空动力学报,2008,23(11): 1953-1960.

Wang B G,Liu S Y,Qian G,et al.Optimization method by combination of wavelet neural networks and genetic algorithm[J].Journal of Aerospace Power,2008,23(11): 1953-1960.(in Chinese)

[21]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.

Deng A D,Zhao L,Bao Y Q,et al.Localization of acoustic emission source based on particle swarm optimizer wavelet neural network[J].Proceedings of the CSEE,2009,29(32): 83-87.(in Chinese)

[22]Marti P,Gonzalez-Altozano P,Lopez-Urrea R,et al.Modeling reference evapotranspiration with calculated targets:assessment and implications[J].Agricultural Water Management,2015, 49:81-90.

[23]曹金峰,李玉中,刘晓英,等.四种参考作物蒸散量综合法的比较[J].中国农业气象,2015,36(4):428-436.

Cao J F,Li Y Z,Liu X Y,et al.Comparison of four combination methods for reference crop evapotranspiration[J].Chinese Journal of Agrometeorology,2015,36(4):428-436.(in Chinese)

机器学习算法和Hargreaves模型在四川盆地ET₀计算中的比较

Comparison of Machine Learning Algorithms and Hargreaves Model for Reference Evapotranspiration Estimation in Sichuan Basin

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	马亚丽, 孙栋元, 张芮, 许健, 王兴繁. 甘肃省参考作物蒸散量时空变异驱动因子分析[J]. 中国农业气象, 2022, 43(11): 881-892.
[2]	王大刚, 于洋, MALIK Ireneusz, WISTUBA Malgorzata, 张敏, 闫小月, 孙凌霄, 于瑞德. 塔里木盆地生长季ET0的时空变化特征及其敏感性分析[J]. 中国农业气象, 2022, 43(05): 340-352.
[3]	刘小飞, 王景雷, 刘祖贵, 宋妮, 方文松. 基于日天气预报数据估算小麦生长季参考作物蒸散量[J]. 中国农业气象, 2022, 43(03): 194-203.
[4]	贾悦, 苏永军, 张冉, 李鹏程, 王凤春, 路梅. 气象资料受限条件下BP神经网络优化模型模拟参考作物蒸散量：以京津冀地区为例[J]. 中国农业气象, 2022, 43(01): 1-16.
[5]	桑玉强, 李龙, 施光耀, 贾长荣, 张劲松. 太行低山区荆条耗水特征及其与参考作物蒸散量的关系[J]. 中国农业气象, 2021, 42(08): 657-665.
[6]	康丽娟，巴特尔·巴克，罗那那，薛亚荣，王孟辉. 阿勒泰地区不同时间尺度参考作物蒸散量的时空变化及影响[J]. 中国农业气象, 2018, 39(08): 502-511.
[7]	杨永刚，崔宁博，胡笑涛，龚道枝，李晨，贾悦. 中国三大灌区参考作物蒸散量温度法模型的修订与适应性评价[J]. 中国农业气象, 2018, 39(06): 357-369.
[8]	杨永刚，崔宁博，胡笑涛，龚道枝. 中国粮食主产区参考作物蒸散量演变特征与成因分析[J]. 中国农业气象, 2018, 39(04): 245-255.
[9]	邹海平，陈汇林，田光辉，陈小敏，白蕤，佟金鹤. 海南岛参考作物蒸散量时空变化特征及成因分析[J]. 中国农业气象, 2018, 39(01): 18-26.
[10]	胡琦，董蓓，潘学标，王潇潇，魏培，赵海涵，张煦庭. 不同时间尺度下华北平原干湿气候时空变化及成因分析[J]. 中国农业气象, 2017, 38(05): 267-277.
[11]	李英杰，延军平，王鹏涛. 北方农牧交错带参考作物蒸散量时空变化与成因分析[J]. 中国农业气象, 2016, 37(02): 166-173.
[12]	李思思，张飞云，白磊，李兰海. 北疆地区生长季参考作物蒸散量的时空变化特征及其敏感性分析[J]. 中国农业气象, 2015, 36(06): 683-691.
[13]	环海军，杨再强，刘岩，夏福华. 鲁中地区参考作物蒸散量时空变化特征及主要气象因子的贡献分析[J]. 中国农业气象, 2015, 36(06): 692-698.
[14]	曹金峰，李玉中，刘晓英，钟秀丽，赵叶萌. 四种参考作物蒸散量综合法的比较[J]. 中国农业气象, 2015, 36(04): 428-436.
[15]	王晓东，马晓群，许莹，刘瑞娜，曹雯，朱浩. 淮河流域参考作物蒸散量变化特征及主要气象因子的贡献分析[J]. 中国农业气象, 2013, 34(06): 661-667.