基于芒种日分析的BP模型在中长期汛期降雨量预报中的应用
|
摘要
为提高汛期降雨量中长期预报的精度,采用芒种日分析充分提取有用信息,基于BP神经网络模型,构建了芒种日分析的BP神经网络耦合模型,并将其应用于北京市中长期汛期降雨量的预测。结果表明:相比于常规BP模型,耦合BP模型能够有效提高预报的精度,验证期耦合BP模型模拟值与实测值相关系数为0.78,明显优于常规BP模型的0.42;耦合BP模型较常规BP模型的预报合格率提高了40%。芒种日分析能够充分发掘隐藏在原始数据中的有用信息,降低极端值等噪声数据对预报结果的影响,有效提高了模型的预报精度。将传统节气与人工智能预报技术相结合,为中长期汛期降雨量预报提供了一种新思路。
In order to improve the accuracy of medium and long-term wet-season rainfall forecasting,a Hybrid models based on the Grain in Ear and BP neural network is established in this study,and applied to the forcasting of rainfall in mid-and long-term wet-seasons in Beijing.The results show that the hybrid model can effectively improve the accuracy of the rainfall forecasting,in comparison with the traditional BP model.The correlation coefficient between the simulated and the measured rainfall is 0.78,which is much better than the traditional BP model of 0.42.The hybrid model also has a 40%improvement in terms of the forecasting pass rate over the traditional BP model.The Grain in Ear can fully explore the useful information hidden in the original data,reduce interfere of noise data(e.g.,extreme values),and effectively improve the forecasting accuracy.This study combines the traditional 24-solar-terms with artificial intelligence forecasting technology and provides a new idea for medium and long-term wet-season rainfall forecasting.
In order to improve the accuracy of medium and long-term wet-season rainfall forecasting,a Hybrid models based on the Grain in Ear and BP neural network is established in this study,and applied to the forcasting of rainfall in mid-and long-term wet-seasons in Beijing.The results show that the hybrid model can effectively improve the accuracy of the rainfall forecasting,in comparison with the traditional BP model.The correlation coefficient between the simulated and the measured rainfall is 0.78,which is much better than the traditional BP model of 0.42.The hybrid model also has a 40%improvement in terms of the forecasting pass rate over the traditional BP model.The Grain in Ear can fully explore the useful information hidden in the original data,reduce interfere of noise data(e.g.,extreme values),and effectively improve the forecasting accuracy.This study combines the traditional 24-solar-terms with artificial intelligence forecasting technology and provides a new idea for medium and long-term wet-season rainfall forecasting.
引文
[1]RIAD S,MANIA J,BOUCHAOU L,et al.Rainfall-runoff model usingan artificial neural network approach[J].Mathematical&Computer Modelling,2007,40(7):839-846.DOI:10.1016/j.mcm.2004.10.012.
[2]张晓伟,沈冰,黄领梅,等.基于BP神经网络的灰色自记忆径流预测模型[J].水力发电学报,2009,28(1):68-71.(ZHANG X W,SHEN B,HUANG L M,et al.Grey self-memory model based on BP neural network for annual Runoff prediction[J].Journal of Hydroelectric Engineering,2009,28(1):68-71.(in Chinese))
[3]桑燕芳,王栋,吴吉春,等.基于WA、ANN和水文频率分析法相结合的中长期水文预报模型的研究[J].水文,2009,29(3):10-15.(SANG Y F,WANG D,WU JC,et al.Research on stochastic eedium-and long-term hydrologic forecasting model based on WA,ANN and hydrologic frequency analysis[J].Journal of China Hydrology,2009,29(3):10-15.(in Chinese))DOI:10.3969/j.issn.1000-0852.2009.03.003.
[4]刘莉,叶文.基于BP神经网络时间序列模型的降水量预测[J].水资源与水工程学报,2010,21(5):156-159.(LIU L,YE W.Precipitation prediction of time series model based on BP artificial neural network[J].Journal of Water Resources&Water Engineering,2010,21(5):156-159.(in Chinese))
[5]ADAMOWSKI J,SUN K.Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds[J].Journal of Hydrology,2010,390(1-2):85-91.DOI:10.1016/j.jhydrol.2010.06.033.
[6]孙娜,周建中,朱双,等.基于小波分析的两种神经网络耦合模型在月径流预测中的应用[J].水电能源科学,2018,36(4):14-17,32.(SUN N,ZHOU J Z,ZHU S,et al.Application of hybrid models based on wavelet analysis and two different neural networks in prediction of monthly runoff[J].Water Resources and Power,2018,36(4):14-17,32.(in Chinese))
[7]卢韦伟,周建中,陈璐,等.考虑预报因子选择的神经网络降雨径流模型[J].水电能源科学,2013,31(6):21-25.(LU W W,ZHOU J Z,CHEN L,et al.Neural network model of rainfall-runoff process considering selection of prediction factors[J].Water Resources and Power,2013,31(6):21-25.(in Chinese))
[8]WANG W C,CHAU K W,LIN Q,et al.Improving forecasting accuracy of medium and long-term runoff using artificial neural network based on EEMD decomposition[J].Environmental Research,2015,139:46-54.DOI:10.1016/j.envres.2015.02.002.
[9]SHOAIB M,SHAMSELDIN A,MELVILLE B,et al.Comparative study of different wavelet based neural network models for rainfall-runoff modeling[J].Journal of Hydrology,2014,515(13):47-58.DOI:10.1016/j.jhydrol.2014.04.055.
[10]郝丽娜,粟晓玲,黄巧玲,等.基于小波广义回归神经网络耦合模型的月径流预测[J].水力发电学报,2016,35(5):47-54.(HAO L N,SU X L,HUANG Q L,et al.Monthly runoff prediction using wavelet transform and generalized regression neural network model[J].Journal of Hydroelectric Engineering,2016,35(5):47-54.(in Chinese))DOI:10.11660/slfdxb.20160506.
[11]李阳,李克飞纪昌明,等.结合均生函数的神经网络在中长期水文预报中的应用[J].水电能源科学,2013,31(2):19-22.(LI Y,LI K F,JI C M,et al.Application of neural network combined with mean generation function to mid longterm hydrological forecasting[J].Water Resources and Power,2013,31(2):19-22.(in Chinese))
[12]刘丹辉,马龙,刘廷玺,等.均生函数与BP神经网络耦合模拟预测模型(MGF-BP-I)的建立与应用[J].水文,2016,36(6):7-15.(LIU D H,MA L,LIU Y X,et al.A coupled simulation and forecast model of mean generating function and BP neural network(MGF-BP-I)[J].Journal of China Hydrology,2016,36(6):7-15.(in Chinese))
[13]CANNAS B,FANNI A,SEE L,et al.Data preprocessing for river flow forecasting using neural net works:wavelet transforms and data partitioning[J].Physics&Chemistry of the Earth Parts A/B/C,2006,31(18):1164-1171.DOI:10.1016/j.pce.2006.03.020.
[14]李永坤,丁晓洁.北京市降水量变化特征分析[J].北京水务,2013(2):9-12.(LI Y K,DING X J.Analysis on the change characteristics of precipitation in Beijing[J].Beijing Water,2013(2):9-12.(in Chinese))DOI:10.3969/j.issn.1673-4637.2013.02.003.
[15]钱诚,严中伟,曹丽娟,等.基于1873年以来器测气温的二十四节气气候变化[J].气候与环境研究,2018,23(6):670-682.(QIAN C,YAN Z W,CAO L J,et al.Climatic changes in the twenty-four solar terms based on temperature observations back to 1873[J].Climatic and Environmental Research,2018,23(6):670-682.(in Chinese))
[16]钱诚,严中伟,符淙斌,等.1960-2008年中国二十四节气气候变化[J].科学通报,2011,56(35):3011-3020.(QIAN C,YAN Z W,FU C B,et al.24solar terms climate change in China from 1960to 2008[J].Chinese Science Bulletin,2011,56(35):3011-3020.(in Chinese))
[17]陈菊英.中国旱涝的分析和长期预报研究[M].农业出版社,1991.(CHEN J Y.Analysis and long-term forecasting of drought and flood in China[M].Agriculture Publishinghouse,1991.(in Chinese))
[18]GB/T 22482-2008,水文情报预报规范[S].(GB/T22482-2008,Standard for Hydrological Information And Hydrological forecasting[S].(in Chinese))
[2]张晓伟,沈冰,黄领梅,等.基于BP神经网络的灰色自记忆径流预测模型[J].水力发电学报,2009,28(1):68-71.(ZHANG X W,SHEN B,HUANG L M,et al.Grey self-memory model based on BP neural network for annual Runoff prediction[J].Journal of Hydroelectric Engineering,2009,28(1):68-71.(in Chinese))
[3]桑燕芳,王栋,吴吉春,等.基于WA、ANN和水文频率分析法相结合的中长期水文预报模型的研究[J].水文,2009,29(3):10-15.(SANG Y F,WANG D,WU JC,et al.Research on stochastic eedium-and long-term hydrologic forecasting model based on WA,ANN and hydrologic frequency analysis[J].Journal of China Hydrology,2009,29(3):10-15.(in Chinese))DOI:10.3969/j.issn.1000-0852.2009.03.003.
[4]刘莉,叶文.基于BP神经网络时间序列模型的降水量预测[J].水资源与水工程学报,2010,21(5):156-159.(LIU L,YE W.Precipitation prediction of time series model based on BP artificial neural network[J].Journal of Water Resources&Water Engineering,2010,21(5):156-159.(in Chinese))
[5]ADAMOWSKI J,SUN K.Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds[J].Journal of Hydrology,2010,390(1-2):85-91.DOI:10.1016/j.jhydrol.2010.06.033.
[6]孙娜,周建中,朱双,等.基于小波分析的两种神经网络耦合模型在月径流预测中的应用[J].水电能源科学,2018,36(4):14-17,32.(SUN N,ZHOU J Z,ZHU S,et al.Application of hybrid models based on wavelet analysis and two different neural networks in prediction of monthly runoff[J].Water Resources and Power,2018,36(4):14-17,32.(in Chinese))
[7]卢韦伟,周建中,陈璐,等.考虑预报因子选择的神经网络降雨径流模型[J].水电能源科学,2013,31(6):21-25.(LU W W,ZHOU J Z,CHEN L,et al.Neural network model of rainfall-runoff process considering selection of prediction factors[J].Water Resources and Power,2013,31(6):21-25.(in Chinese))
[8]WANG W C,CHAU K W,LIN Q,et al.Improving forecasting accuracy of medium and long-term runoff using artificial neural network based on EEMD decomposition[J].Environmental Research,2015,139:46-54.DOI:10.1016/j.envres.2015.02.002.
[9]SHOAIB M,SHAMSELDIN A,MELVILLE B,et al.Comparative study of different wavelet based neural network models for rainfall-runoff modeling[J].Journal of Hydrology,2014,515(13):47-58.DOI:10.1016/j.jhydrol.2014.04.055.
[10]郝丽娜,粟晓玲,黄巧玲,等.基于小波广义回归神经网络耦合模型的月径流预测[J].水力发电学报,2016,35(5):47-54.(HAO L N,SU X L,HUANG Q L,et al.Monthly runoff prediction using wavelet transform and generalized regression neural network model[J].Journal of Hydroelectric Engineering,2016,35(5):47-54.(in Chinese))DOI:10.11660/slfdxb.20160506.
[11]李阳,李克飞纪昌明,等.结合均生函数的神经网络在中长期水文预报中的应用[J].水电能源科学,2013,31(2):19-22.(LI Y,LI K F,JI C M,et al.Application of neural network combined with mean generation function to mid longterm hydrological forecasting[J].Water Resources and Power,2013,31(2):19-22.(in Chinese))
[12]刘丹辉,马龙,刘廷玺,等.均生函数与BP神经网络耦合模拟预测模型(MGF-BP-I)的建立与应用[J].水文,2016,36(6):7-15.(LIU D H,MA L,LIU Y X,et al.A coupled simulation and forecast model of mean generating function and BP neural network(MGF-BP-I)[J].Journal of China Hydrology,2016,36(6):7-15.(in Chinese))
[13]CANNAS B,FANNI A,SEE L,et al.Data preprocessing for river flow forecasting using neural net works:wavelet transforms and data partitioning[J].Physics&Chemistry of the Earth Parts A/B/C,2006,31(18):1164-1171.DOI:10.1016/j.pce.2006.03.020.
[14]李永坤,丁晓洁.北京市降水量变化特征分析[J].北京水务,2013(2):9-12.(LI Y K,DING X J.Analysis on the change characteristics of precipitation in Beijing[J].Beijing Water,2013(2):9-12.(in Chinese))DOI:10.3969/j.issn.1673-4637.2013.02.003.
[15]钱诚,严中伟,曹丽娟,等.基于1873年以来器测气温的二十四节气气候变化[J].气候与环境研究,2018,23(6):670-682.(QIAN C,YAN Z W,CAO L J,et al.Climatic changes in the twenty-four solar terms based on temperature observations back to 1873[J].Climatic and Environmental Research,2018,23(6):670-682.(in Chinese))
[16]钱诚,严中伟,符淙斌,等.1960-2008年中国二十四节气气候变化[J].科学通报,2011,56(35):3011-3020.(QIAN C,YAN Z W,FU C B,et al.24solar terms climate change in China from 1960to 2008[J].Chinese Science Bulletin,2011,56(35):3011-3020.(in Chinese))
[17]陈菊英.中国旱涝的分析和长期预报研究[M].农业出版社,1991.(CHEN J Y.Analysis and long-term forecasting of drought and flood in China[M].Agriculture Publishinghouse,1991.(in Chinese))
[18]GB/T 22482-2008,水文情报预报规范[S].(GB/T22482-2008,Standard for Hydrological Information And Hydrological forecasting[S].(in Chinese))
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |