变化环境下水文模型时变参数的识别及函数型式构建

Identifying Functional Form of Time-Varying Hydrological Model Parameters under Changing Environment

选用两参数月水量平衡模型,采用集合卡尔曼滤波算法识别水文模型参数时变过程,通过模型参数与气候因子的相关性分析,构建了参数与降水、潜在蒸散发和气温的线性函数。以美国MOPEX数据库的3个流域为研究对象,利用1983~2003年的月水文数据进行实例研究,结果表明：相较于常数参数方案,考虑时变型式参数的模型在率定期和检验期的径流模拟纳什效率系数可分别提高18%和17%,且对峰值的模拟更优;通过典型干旱年（1999~2001年）与湿润年（2003年）分析降水变化对径流的影响,发现以往将参数视为常数会低估径流的变化,低估量最高可达38%,而时变参数方案可将径流变化量误差降至7%。因此,将水文模型参数考虑为气候因子的函数型式更有利于变化环境下径流预测的准确性。

A two-parameter monthly water balance model was chosen to establish the functional forms of model parameters. The ensemble Kalman filter technique was used first to identify the time-varying parameters, following the construction of the linear functions of parameters and precipitation, potential evapotranspiration and temperature via the correlation analysis between model parameters and climatic factors. The case study was carried out in three Model Parameter Estimation Experiment（MOPEX） catchments in USA using the hydrological data from 1983 to 2003, in which the periods from 1999 to 2001 were selected as droughty year, while 2003 was selected as wet year. The results indicated that： 1） The accuracy of runoff simulations was improved when considering the model parameters as time-varying, especially in peak flows. The Nash-Sutcliffe efficiency coefficient of runoff was increased by 18% and 17% for the calibration and validation periods, respectively; 2） the change of runoff was underestimated when considering the model parameters as constant, with the relative error being up to 38%, while its value was reduced to 7% when considering the model parameters as time-varying. Therefore, taking the hydrological model parameters as a function of climate factors led to a significant enhancement in runoff prediction under changing environment.