摘要
选取西南喀斯特地区4个气象站点(都安、河池、百色和融安)5 a(2008—2012年)的逐日气象数据,包括日最高气温Tmax、日最低气温T_(min)、相对湿度R_H、日照时数n和风速u2这5个气象因子的不同组合作为输入,并以FAO 56 Penman-Monteith法(FAO P-M)的计算结果作为标准值,建立基于随机森林(Random forest,RF)算法和基因表达式编程(Gene expression programming,GEP)算法的ET0模型,并将模拟结果与传统Hargreaves模型的计算结果进行比较。结果表明,不同气象因子组合下建立的RF模型均能较好地反映气象因子与ET0之间的非线性关系。随着气象因子的增加,RF模型模拟的精度随之提高。在仅有气温数据时,RF模型仍具有足够的精度(R^2为0.875,RMSE为0.546 mm/d),与传统Hargreaves模型相比R2平均增加了1.98%,RMSE平均减小了22.88%,因此在仅有气温数据时可用RF模型代替Hargreaves模型。RF算法对气象因子的重要性评估表明,在该区域对ET_0最重要的气象因子依次为T_(max)、n、T_(min)、R_a、R_H和u_2。相同气象因子输入下,RF模型精度高于GEP模型。
Accurate estimation of reference evapotranspiration （ET0） is very important in hydrological cycle research, and it is also essential in agricultural water management and allocation. Using less meteorological parameters to estimate ET0 is necessary in areas with limited data. The ability of random forest （RF） and gene expression programming （GEP） algorithm in modeling ET0 was investigated and compared by using fewer meteorological parameters collected from four weather stations of Duan, Hechi, Baise and Rong＇ an, in karst region of southwest China, over a five-year period （2008--2012）. Daily climatic data of the four stations, including maximum temperature （ T ） , minimum temperature （Tmax） , sunshine duration （n）, relative humidity （RH） and wind speed （U2） were employed to model ETo by using FAO 56 Penman - Monteith equation as the reference, and their performances were evaluated using determination coefficient （R2） and root mean square error （RMSE）. From the statistical results, the derived RF-based （R2 was ranged from 0. 809 to O. 991, and RMSE was ranged from O. 158 mm/d to O. 678 mm/d） and GEP-based （R2 was in range of 0. 830 -0. 977, and RMSE was in range of 0. 225 - O. 645 mm/d） ET0 models were successfully applied to model ET0 with diftbrent input combinations. When only the temperature data can he used, the RF models produced satisfactory results （R^2 = 0. 875, RMES =0. 546 mm/d） , which can be used as an alternative to the conventional Hargreaves model. The relative importance of meteorological variables for ET0 can be assessed by RF method, the order of the relative importance of meteorological variables was ： Tmax, n,Tmin , R, RH and u2. In most cases, the RF models were found to perform better than the GEP models. The results were expected to be useful to guide rehabilitation strategies and agricultural water management in karst region of Southwest China.
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2017年第3期302-309,共8页
Transactions of the Chinese Society for Agricultural Machinery
基金
国家重点基础研究发展计划(973计划)项目(2015CB452703)
国家自然科学基金项目(41171187
31100294)
