基于PSO-BP神经网络的西洞庭湖南咀站径流预测
|
摘要
为建立因子少、预报周期短、预报精度高的西洞庭湖控制性水文站南咀站的月平均径流量预报模型,通过对松滋-太平水系控制性水文站安乡、澧水控制性水文站石龟山站月平均水位、流量以及沙湾站月平均水位进行相关性、因子贡献率分析,确定输入因子,借助PSO-BP神经网络对南咀站1956年1月至2005年12月各月平均径流量进行训练,获取网络结构及参数进而预测2006年1月至2008年12月各月径流量。结果表明:①石龟山、安乡站水位对南咀站月平均径流量影响最显著;②汛期、非汛期的划分一定程度上可提高南咀站月平均径流量预报精度;③以安乡、石龟山站月平均水位、流量以及沙湾站月平均水位作为输入因子,PSO-BP神经网络预报效果最好,合格率77.8%,预报等级为乙级;④基于相关性、因子贡献率分析,将安乡、石龟山站作为输入因子,预报合格率降为61.1%,预报等级降为丙级,但仍满足预报要求。
To establish a monthly average runoff forecast model for Nanzui station in West Dongting Lake with less factors, short forecast periods and high forecasting accuracy, we analyzed the relationship between the monthly average water level and runoff at Anxiang Station(Songzi-Taiping water system controlling hydrological station) and Shiguishan Station(Lishui River controlling hydrological station), and the monthly average water level at Shawan Station(Muping controlling hydrological station). Furthermore, the factor contribution rate to monthly average runoff was calculated and the input factor was determined according to the calculated correlation coefficients and factor contribution rates. Based on the above analysis, we used the PSO-BP neural network to train the average monthly runoff from 1956.1 to 2005.12 at Nanzui Station to obtain the network structure and parameters for forecasting monthly runoff from 2006.1 to 2008.12. The results showed that: ① The water level of Shiguishan and Anxiang station had the most significant effect on the monthly average runoff of Nanzui station; ② The division of non-flood and flood seasons could increase the forecast accuracy of the monthly average runoff of Nanzui Station to some extent; ③Importing the variables, including the monthly average water level and runoff at Shiguishan station and Anxiang station, and the monthly average water level at Shawan station, the PSO-BP neural network had the best forecast effect with 77.8% qualified rate and B forecast grade. ④ Importing the monthly average water level of Anxiang and Shiguishan stations and by correlation and factor contribution rate analysis, the forecasting qualified rate was reduced to 61.1%, and the forecasting level was degraded to C level, but the forecasting requirements were still met.
To establish a monthly average runoff forecast model for Nanzui station in West Dongting Lake with less factors, short forecast periods and high forecasting accuracy, we analyzed the relationship between the monthly average water level and runoff at Anxiang Station(Songzi-Taiping water system controlling hydrological station) and Shiguishan Station(Lishui River controlling hydrological station), and the monthly average water level at Shawan Station(Muping controlling hydrological station). Furthermore, the factor contribution rate to monthly average runoff was calculated and the input factor was determined according to the calculated correlation coefficients and factor contribution rates. Based on the above analysis, we used the PSO-BP neural network to train the average monthly runoff from 1956.1 to 2005.12 at Nanzui Station to obtain the network structure and parameters for forecasting monthly runoff from 2006.1 to 2008.12. The results showed that: ① The water level of Shiguishan and Anxiang station had the most significant effect on the monthly average runoff of Nanzui station; ② The division of non-flood and flood seasons could increase the forecast accuracy of the monthly average runoff of Nanzui Station to some extent; ③Importing the variables, including the monthly average water level and runoff at Shiguishan station and Anxiang station, and the monthly average water level at Shawan station, the PSO-BP neural network had the best forecast effect with 77.8% qualified rate and B forecast grade. ④ Importing the monthly average water level of Anxiang and Shiguishan stations and by correlation and factor contribution rate analysis, the forecasting qualified rate was reduced to 61.1%, and the forecasting level was degraded to C level, but the forecasting requirements were still met.
引文
[1] 唐道来.水利工程建设与生态环境可持续发展的相关性[J].水利技术监督,2015,23(5):36-37.
[2] 王福振.人工神经网络结合SWAT模型在河道径流量预测中的应用[J].水资源开发与管理,2017(8):67-70.
[3] 刘勇,王银堂,陈元芳,等.丹江口水库秋汛期长期径流预报[J].水科学进展,2010,21(6):771-778.
[4] Tootle G A,Singh A K,Piechota T C,et al.Long lead-time forecasting of US streamflow using partial least squares regression[J].Journal of Hydrologic Engineering,2007,12(5):442-451.
[5] 陈瑜彬,杨文发.基于水量平衡的月水资源量长期预测方案探讨[J].人民长江,2013,44(11):9-13.
[6] 陈果,尚松浩,雷志栋.类比合成方法在干旱区内陆河径流量预报中的应用[J].干旱区地理,2004,27(3):287-292.
[7] 席东洁,赵雪花,张永波,等.基于经验模态分解与Elman神经网络的月径流预测[J].中国农村水利水电,2017(7):112-115.
[8] 黄巧玲,粟晓玲,杨家田.基于小波分解的日径流支持向量机回归预测模型[J].西北农林科技大学学报:自然科学版,2016,44(4):211-217.
[9] 杨易华,罗伟伟.基于KPCA-PSO-SVM的径流预测研究[J].人民长江,2017,48(3):44-47.
[10] 聂敏,刘志辉,刘洋,等.基于PCA和BP神经网络的径流预测[J].中国沙漠,2016,36(4):1144-1152.
[11] 李佳,王黎,马光文,等.LS-SVM在径流预测中的应用[J].中国农村水利水电,2008(5):8-10.
[12] 张秀玲,赵文保,李少清,等.基于人工蜂群算法的Elman网络板形预测[J].沈阳大学学报:自然科学版,2012,24(3):38-42.
[13] 杨洁.基于GA优化的RBF网络算法[J].广西科学院学报,2013,29(4):262-264.
[14] 吕艳.“后三峡时代”西洞庭湖防汛抗灾形势与对策[J].现代农业科技,2015(14):201-202.
[15] 吴定宪.西洞庭湖区的洪灾成因及治理对策[J].中国防汛抗旱,2000(1):14-15.
[16] 石林,曾光明,刘卡波,等.复杂河网平原地区的防洪调度决策——基于洪水灾害时空模拟的西洞庭湖冲柳地区案例研究[J].自然灾害学报,2010(2):28-31.
[17] 高彦春,王金凤,封志明.白洋淀流域气温、降水和径流变化特征及其相互响应关系[J].中国生态农业学报,2017,25(4):467-477.
[18] 韩敏,魏茹.基于相空间同步的多变量序列相关性分析及预测[J].系统工程与电子技术,2010,32(11):2426-2430.
[19] 王随继,闫云霞,颜明,等.皇甫川流域降水和人类活动对径流量变化的贡献率分析——累积量斜率变化率比较方法的提出及应用[J].地理学报,2012,67(3):388-397.
[20] 柳烨,赵文刚,杨珮珮,等.基于湿度的ET0估算模型应用研究[J].灌溉排水学报,2016,35(2):35-39.
[21] 金修鹏,李春生.PSO-BP神经网络在多输出水利定额编制中的应用[J].人民长江,2018,49(5):84-88.
[22] 王小川.MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.
[23] 洪卫,廖鸿志.2006年长江流域抗旱的反思与对策[J].人民长江,2007,38(8):61-63.
[2] 王福振.人工神经网络结合SWAT模型在河道径流量预测中的应用[J].水资源开发与管理,2017(8):67-70.
[3] 刘勇,王银堂,陈元芳,等.丹江口水库秋汛期长期径流预报[J].水科学进展,2010,21(6):771-778.
[4] Tootle G A,Singh A K,Piechota T C,et al.Long lead-time forecasting of US streamflow using partial least squares regression[J].Journal of Hydrologic Engineering,2007,12(5):442-451.
[5] 陈瑜彬,杨文发.基于水量平衡的月水资源量长期预测方案探讨[J].人民长江,2013,44(11):9-13.
[6] 陈果,尚松浩,雷志栋.类比合成方法在干旱区内陆河径流量预报中的应用[J].干旱区地理,2004,27(3):287-292.
[7] 席东洁,赵雪花,张永波,等.基于经验模态分解与Elman神经网络的月径流预测[J].中国农村水利水电,2017(7):112-115.
[8] 黄巧玲,粟晓玲,杨家田.基于小波分解的日径流支持向量机回归预测模型[J].西北农林科技大学学报:自然科学版,2016,44(4):211-217.
[9] 杨易华,罗伟伟.基于KPCA-PSO-SVM的径流预测研究[J].人民长江,2017,48(3):44-47.
[10] 聂敏,刘志辉,刘洋,等.基于PCA和BP神经网络的径流预测[J].中国沙漠,2016,36(4):1144-1152.
[11] 李佳,王黎,马光文,等.LS-SVM在径流预测中的应用[J].中国农村水利水电,2008(5):8-10.
[12] 张秀玲,赵文保,李少清,等.基于人工蜂群算法的Elman网络板形预测[J].沈阳大学学报:自然科学版,2012,24(3):38-42.
[13] 杨洁.基于GA优化的RBF网络算法[J].广西科学院学报,2013,29(4):262-264.
[14] 吕艳.“后三峡时代”西洞庭湖防汛抗灾形势与对策[J].现代农业科技,2015(14):201-202.
[15] 吴定宪.西洞庭湖区的洪灾成因及治理对策[J].中国防汛抗旱,2000(1):14-15.
[16] 石林,曾光明,刘卡波,等.复杂河网平原地区的防洪调度决策——基于洪水灾害时空模拟的西洞庭湖冲柳地区案例研究[J].自然灾害学报,2010(2):28-31.
[17] 高彦春,王金凤,封志明.白洋淀流域气温、降水和径流变化特征及其相互响应关系[J].中国生态农业学报,2017,25(4):467-477.
[18] 韩敏,魏茹.基于相空间同步的多变量序列相关性分析及预测[J].系统工程与电子技术,2010,32(11):2426-2430.
[19] 王随继,闫云霞,颜明,等.皇甫川流域降水和人类活动对径流量变化的贡献率分析——累积量斜率变化率比较方法的提出及应用[J].地理学报,2012,67(3):388-397.
[20] 柳烨,赵文刚,杨珮珮,等.基于湿度的ET0估算模型应用研究[J].灌溉排水学报,2016,35(2):35-39.
[21] 金修鹏,李春生.PSO-BP神经网络在多输出水利定额编制中的应用[J].人民长江,2018,49(5):84-88.
[22] 王小川.MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.
[23] 洪卫,廖鸿志.2006年长江流域抗旱的反思与对策[J].人民长江,2007,38(8):61-63.