Runoff and sediment yield from an Indian watershed during the monsoon period were forecasted for differ-ent time periods (daily and weekly) using the back propagation artificial neural network (BPANN) modeling techniq...Runoff and sediment yield from an Indian watershed during the monsoon period were forecasted for differ-ent time periods (daily and weekly) using the back propagation artificial neural network (BPANN) modeling technique. The results were compared with those of single- and multi-input linear transfer function models. In BPANN, the maximum value of variable was considered for normalization of input, and a pattern learning algorithm was developed. Input variables in the model were obtained by comparing the response with their respective standard error. The network parsimony was achieved by pruning the network using error sensitiv-ity - weight criterion, and model generalization by cross validation. The performance was evaluated using correlation coefficient (CC), coefficient of efficiency (CE), and root mean square error (RMSE). The single input linear transfer function (SI-LTF) runoff and sediment yield forecasting models were more efficacious than the multi input linear transfer function (MI-LTF) and ANN models.展开更多
径流曲线数模型(Soil Conservation Service Curve Number Model,简称SCS-CN模型)可以利用降雨资料估算径流,对水资源合理配置和山洪灾害预警具有重要意义,因为其方便计算、参数简单,而被广泛应用。目前标准SCS-CN模型在山区小流域的适...径流曲线数模型(Soil Conservation Service Curve Number Model,简称SCS-CN模型)可以利用降雨资料估算径流,对水资源合理配置和山洪灾害预警具有重要意义,因为其方便计算、参数简单,而被广泛应用。目前标准SCS-CN模型在山区小流域的适用性欠佳,因此需要对模型参数进行优化以提高预测精度。本文以湖南省螺岭桥流域为例,根据实测降雨径流资料优化径流曲线数CN(Curve Number)查算表,并利用步长优化参数算法研究初损率对模型精度的影响,将优化模型的方法应用于湖南省凤凰小流域,验证该优化方法的可靠性。结果分析表明:与标准SCS-CN模型相比,优化后的SCS-CN模型效率系数NSE从0.576提升至0.813,决定系数R^(2)为0.858。将模型优化方法验证于气候地形条件相似的凤凰流域,模型NSE值提高117%。通过预测径流深与实测径流深比较,优化模型模拟精度较为理想,对湖南省山区小流域场次降雨产流预报有一定的参考意义。展开更多
文摘Runoff and sediment yield from an Indian watershed during the monsoon period were forecasted for differ-ent time periods (daily and weekly) using the back propagation artificial neural network (BPANN) modeling technique. The results were compared with those of single- and multi-input linear transfer function models. In BPANN, the maximum value of variable was considered for normalization of input, and a pattern learning algorithm was developed. Input variables in the model were obtained by comparing the response with their respective standard error. The network parsimony was achieved by pruning the network using error sensitiv-ity - weight criterion, and model generalization by cross validation. The performance was evaluated using correlation coefficient (CC), coefficient of efficiency (CE), and root mean square error (RMSE). The single input linear transfer function (SI-LTF) runoff and sediment yield forecasting models were more efficacious than the multi input linear transfer function (MI-LTF) and ANN models.
文摘径流曲线数模型(Soil Conservation Service Curve Number Model,简称SCS-CN模型)可以利用降雨资料估算径流,对水资源合理配置和山洪灾害预警具有重要意义,因为其方便计算、参数简单,而被广泛应用。目前标准SCS-CN模型在山区小流域的适用性欠佳,因此需要对模型参数进行优化以提高预测精度。本文以湖南省螺岭桥流域为例,根据实测降雨径流资料优化径流曲线数CN(Curve Number)查算表,并利用步长优化参数算法研究初损率对模型精度的影响,将优化模型的方法应用于湖南省凤凰小流域,验证该优化方法的可靠性。结果分析表明:与标准SCS-CN模型相比,优化后的SCS-CN模型效率系数NSE从0.576提升至0.813,决定系数R^(2)为0.858。将模型优化方法验证于气候地形条件相似的凤凰流域,模型NSE值提高117%。通过预测径流深与实测径流深比较,优化模型模拟精度较为理想,对湖南省山区小流域场次降雨产流预报有一定的参考意义。
