基于日照时数的太阳辐射通用模型提升参考作物蒸散估算精度研究

Determination of Generalized Solar Radiation Model Based on Sunshine Percentage for Improving Reference Crop Evapotranspiration Estimation Accuracy

准确的太阳辐射(R_(s))信息是农业、气象和能源等领域和业务部门的重要基础资料,但R_(s)的可靠观测在全球极具挑战。利用中国96个辐射站1967-2016年观测数据,评估了32个(S1~S32)基于日照时数估算R_(s)的模型精度,确定了适用于无R_(s)观测区的最佳通用模型,并最终更新了FAO56推荐的Penman-Monteith方程参考作物蒸散量(ET_(0))中R_(s)的计算方法。结果表明,S18~S32模型的表现较好且接近,其适用于单站点的模型回归系数、决定系数、均方根误差(RMSE)、相对均方根误差(RRMSE)和模型效率的均值分别为0.975~0.976、0.882~0.886、2.368~2.412 MJ/(m^(2)·d)、0.171~0.175和0.881~0.885。进一步对S18~S32模型进行一般化后发现S18模型仅需3个参数,估算精度较高且稳定性好,推荐该模型为中国无辐射观测区估算日R_(s)的通用模型。基于通用S18模型估算R_(s)进而计算的ET_(0)比FAO56推荐的基于S9模型计算结果精度更高,其RMSE和RRMSE均值分别降低了12.9%和13.9%,因此推荐采用该方法更新FAO56 Penman-Monteith方程中R_(s)估算公式。

Accurate solar radiation(R_(S))data are crucial for research fields and business departments such as agriculture,hydrology,meteorology,ecology,and energy in environmental evaluation.Based on the radiation data of 96 stations in China from 1967 to 2016,the accuracy of 32(S1~S32)solar radiation models was evaluated based on sunshine hours,the best general model was constructed,and its impact on calculating reference crop evapotranspiration(ET_(0))was analyzed.The results showed that the S18~S32 models performed better.The average values of regression coefficient(b),determination coefficient(R^(2)),root mean square error(RMSE),relative root mean square error(RRMSE)and model efficiency(EF)of single site model were 0.975~0.976,0.882~0.886,2.368~2.412 MJ/(m^(2)·d),0.171~0.175 and 0.881~0.885 for S18~S32 models,respectively.The results of evaluating the general models for S18~S32 showed that the S18 model had higher accuracy and better model stability with only three input parameters,and the mean values of b R^(2),RMSE,RRMSE and EF were 0.974,0.881,2.626 MJ/(m^(2)·d),0.184 and 0.881 for S18 model.The S18 model was recommended to be a general estimation formula of daily R_(S)in China with or without R_(S)observation area.Compared with the method recommended by FAO 56,the ET_(0)results calculated based on the general S18 model reduce the mean values of RMSE and RRMSE by 12.9% and 13.9%,respectively.