欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
基于人工神经网络的非线性扰动模型（NLPM—ANN）充分利用了LPM的季节信息处理方法和ANN强大的非线性模拟性能．然而该模型没有考虑流域的前期土壤湿度状态，影响了模型的模拟预报精度．为了将流域的前期土湿加入模型，同时能更加充分利用降水信息，采取一种将LPM与ANN结合起来的联合预报模式．选用8个流域的降雨径流资料，对改进的NLPM—ANN模型与SLM—ANN和NLPM-ANN模型进行比较研究．计算结果表明，改进的NLPM—ANN模型优于SLM-ANN模型和NLPM—ANN，在率定期和检验期的模型效率相对增值指数较NLPM—ANN提高10％左右．
英文摘要：
NLPM-ANN model takes advantage of the consideration of seasonal information by LPM and the notable nonlinear simulation capability of ANN. However, that this model does not take account of antecedent catchment wetness and the use of rainfall information is not enough; and it effects the simulation and forecasting accuracy. To take the consideration of antecedent catchment wetness and use of more rainfall information, a modified NLPM-ANN model is proposed to couple LPM and ANN together. The rainfall-runoff data of eight catchments are selected and used to compare the modified NLPM-ANN with SLM- ANN and NLPM-ANN models. Results show that the modified NLPM-ANN model performs much better than NLPM-ANN and SLM-ANN. The model component efficiency index of the modified model is about 10% over NLPM-ANN during calibration and verification period.
同期刊论文项目
同项目期刊论文
Historical temporal trends of hydro-climatic variables and runoff response to climate variability an
期刊信息
位置：