摘要
针对Penman Monteith公式的应用局限性,以公共天气预报可测因子及历史气象数据计算ET0为基准,对广州站2017-01-01-2019-03-31预报气象信息风力状况进行量化后,以2017,2018年气象预报信息为输入因子、ET0为输出因子,分别建立基于回归型支持向量机(SVR)预报模型与BP神经网络预报模型,选择性能较优预报模型对2019年ET0进行预报,并与计算值进行对比分析.结果表明:回归型支持向量机参考作物腾发量预报模型测试集确定性系数为0. 896、均方误差为0. 206,BP神经网络参考作物腾发量预报模型测试集确定性系数为0.851、均方误差为0. 305,SVR参考作物腾发量预报模型均方误差及决定系数要明显优于BP神经网络;基于SVR模型的预报值与PM公式计算值相关系数为0. 761,没有明显差异,表现出显著的相关性以及整体吻合度,可为灌溉预报及决策提供较为准确的ET0预报数据.
For Penman Monteith formula application limitations,using public weather forecast measurable factors and historical meteorological data to calculate ET0 as a benchmark,after quantifying the wind conditions of the meteorological information forecasted by Guangzhou Station from 2017-01-01 to 2019-03-31,with 2017 and 2018 meteorological forecast information as input factors and ET0 as output factors,a regression support vector machines( SVR) forecasting model and BP neural network prediction model were established respectively. A better forecasting model was selected to forecast ET0 of 2019 and compared with the calculated values. Results show that the regression support vector machines reference crop evapotranspiration forecasting model test set mean square error is 0. 206,deterministic coefficient is 0. 896,the amount of BP neural network reference crop evapotranspiration forecasting model test set mean square error is 0. 305,deterministic coefficient is 0. 851,the SVR amount of reference crop evapotranspiration forecasting model is obviously better than the mean square error and the correlation factor to the BP neural network. The correlation coefficient between the predicted value based on the SVR model and the calculated value based on the PM formula is 0. 761,showing no significant difference,but significant correlation and overall coincidence,which can provide relatively accurate ET0 forecast data for irrigation forecasting and decision-making.
作者
江显群
陈武奋
邵金龙
JIANG Xianqun;CHEN Wufen;SHAO Jinlong(Pearl River Water Resources Commission of the Ministry of Water Resources,Guangzhou,Guangdong 510610,China)
出处
《排灌机械工程学报》
EI
CSCD
北大核心
2019年第12期1077-1081,共5页
Journal of Drainage and Irrigation Machinery Engineering
基金
广州市科技计划项目(201604020049)
