检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]黄河水利科学研究院,河南郑州450003 [2]焦作黄河河务局,河南焦作454001
出 处:《人民黄河》2017年第12期146-149,153,共5页Yellow River
摘 要:为实现灌区引黄用水预测,以多元回归与神经网络为基本手段,建立BP神经网络、小波神经网络、逐步回归、基于模糊贴近度的回归分析等4种引黄用水月预测模型。通过各模型预测值与实测值的比较,并以模型模拟效率系数NSC(NSC=0.75为阈值)为评价指标,分析表明:4种模型均可预测各地引黄用水变化情况,但模拟精度不同。在宁蒙地区4种模型均能满足预测精度要求;河南省除小波神经网络模型外,其他模型均能满足预测精度要求;山东省则仅有BP神经网络与逐步回归模型能满足预测精度要求。For realizing the Yellow River water consumption prediction in the irrigation areas,this paper established four models to forecastthe monthly Yellow River water consumption by using the multiple regression and neural network methods. By comparing the predicted andthe measured values and taking the efficiency coefficient ( NSC,threshhold value is 0 .7 5 ) as the evaluation indicator,the results show thatall of the four models can predict the water consumption variation of different irrigation areas, while the prediction accuracy is different. All ofthe four models can meet the prediction accuracy requirements in the Ningxia-Inner Mongolia area ; besides the wavelet model, the other threemodels can meet the prediction accuracy requirements in Henan Province ; while in the Shandong Province,only the BP model and the step-wise regression model can meet the prediction accuracy.
分 类 号:S274.4[农业科学—农业水土工程] TV882.1[农业科学—农业工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.229