基于随机森林的长短期记忆网络气温预测
|
摘要
针对气象数据多为时间序列,而传统预测方法没有将时间相关性考虑在内,导致预测准确率低的问题,提出一种基于随机森林的长短期记忆网络气温预测模型。利用随机森林选择出与气温高度相关的气象要素作为输入变量,消除原始气象数据中的噪音、降低网络的复杂度,在此基础上利用长短期记忆网络建立总体预测模型,在采集的多要素气象数据上进行实验。实验结果表明,该模型在处理大规模多变量的时间序列数据时具有较高的预测精度和较强的泛化能力。
Aiming at the problem that meteorological data are mostly time series,while traditional prediction methods do not take time correlation into account,which results in low prediction accuracy,a temperature prediction model using long short term memory network based on random forest was proposed.The characteristic that meteorological elements are highly correlated with the temperature was selected as input variables using random forest to eliminate the noise in the original meteorological data and reduce the complexity of the network.On this basis,the long short term memory network was used to establish the overall prediction model,and the experiment was carried out on the collected multi element meteorological data.Experimental results show that the proposed model has high prediction accuracy and strong generalization ability in dealing with large scale multivariable time series data.
Aiming at the problem that meteorological data are mostly time series,while traditional prediction methods do not take time correlation into account,which results in low prediction accuracy,a temperature prediction model using long short term memory network based on random forest was proposed.The characteristic that meteorological elements are highly correlated with the temperature was selected as input variables using random forest to eliminate the noise in the original meteorological data and reduce the complexity of the network.On this basis,the long short term memory network was used to establish the overall prediction model,and the experiment was carried out on the collected multi element meteorological data.Experimental results show that the proposed model has high prediction accuracy and strong generalization ability in dealing with large scale multivariable time series data.
引文
[1]AI Beibei,ZHAO Wenhua,WAN You.Research on spatial correlation pattern mining of extreme temperature events in China[J].Geographic Information World,2014,21(4):6-12(in Chinese).[艾贝贝,赵雯华,万幼.全国极端气温事件的空间关联模式挖掘研究[J].地理信息世界,2014,21(4):6-12.]
[2]Abuella M,Chowdhury B.Solar power probabilistic forecasting by using multiple linear regression analysis[C]//Southeastcon.IEEE,2015:1-5.
[3]Pratiher S,Mukhopadhyay S,Barman R,et al.Recurrence quantification&ARIMA based forecasting of rainfall-temperature dynamics[C]//International Conference on Signal Processing and Communication,2016:490-495.
[4]Huang C Y,Liu Y W,Tzeng W C,et al.Short term wind speed predictions by using the grey prediction model based forecast method[C]//Green Technologies Conference.IEEE,2011:1-5.
[5]Jose C,Goyal P,Aggrwal P,et al.Local deep kernel learning for efficient non-linear SVM prediction[C]//International Conference on International Conference on Machine Learning.JMLR.org,2013:III-486.
[6]Venkadesh S,Hoogenboom G,Potter W,et al.A genetic algorithm to refine input data selection for air temperature prediction using artificial neural networks[J].Applied Soft Computing Journal,2013,13(5):2253-2260.
[7]ZHU Jingjing,ZHAO Xiaoping,WU Sheng’an,et al.Research on hainan air temperature prediction model based on support vector machine[J].Journal of Hainan University(Natural Science Edition),2016,34(1):40-44(in Chinese).[朱晶晶,赵小平,吴胜安,等.基于支持向量机的海南气温预测模型研究[J].海南大学学报(自然科学版),2016,34(1):40-44.]
[8]NIU Zhijuan,HU Hongping.Prediction model of monthly mean air temperature based on principal component analysis and BP neural network and RBF neural network[J].High School Science Journal,2015,35(11):6-8(in Chinese).[牛志娟,胡红萍.基于主成分分析的BP神经网络和RBF神经网络月平均气温预测模型[J].高师理科学刊,2015,35(11):6-8.]
[9]ZHOU Guobing.Recurrent neural network with minimal gate structure and its application[D].Nanjing:Nanjing University,2016(in Chinese).[周国兵.最少门结构的循环神经网络及其应用[D].南京:南京大学,2016.]
[10]CAO Yuhui.A study of text emotion analysis based on depth learning[D].Harbin:Harbin Institute of Technology,2016(in Chinese).[曹宇慧.基于深度学习的文本情感分析研究[D].哈尔滨:哈尔滨工业大学,2016.]
[11]LU Zenan,SHANG Yulin.Steel price forecast based on LSTM neural network model[J].Technology Horizon,2017(13):116-117(in Chinese).[陆泽楠,商玉林.基于LSTM神经网络模型的钢铁价格预测[J].科技视界,2017(13):116-117.]
[12]YAO Dengju,YANG Jing,ZHAN Xiaojuan.Feature selection algorithm based on random forest[J].Journal of Jilin University(Engineering),2014,44(1):137-141(in Chinese).[姚登举,杨静,詹晓娟.基于随机森林的特征选择算法[J].吉林大学学报(工),2014,44(1):137-141.]
[13]ZHOU Jianqiang,LI Yuna,QU Weidong,et al.Prediction of ultra-short term wind speed based on BP neural network and wind speed and space information[J].Power Grid and Clean Energy,2016,31(4):109-112(in Chinese).[周建强,李玉娜,屈卫东,等.基于风速时空信息的BP神经网络超短期风速预测研究[J].电网与清洁能源,2016,31(4):109-112.]
[14]WANG Huizhong,LIU Ke,ZHU Hongyi.Power system load forecasting based on cloud model and RBF support vector machine[J].Journal of Lanzhou University of Technology,2016,42(4):85-88(in Chinese).[王惠中,刘轲,朱宏毅.基于云模型RBF支持向量机的电力系统负荷预测[J].兰州理工大学学报,2016,42(4):85-88.]
[2]Abuella M,Chowdhury B.Solar power probabilistic forecasting by using multiple linear regression analysis[C]//Southeastcon.IEEE,2015:1-5.
[3]Pratiher S,Mukhopadhyay S,Barman R,et al.Recurrence quantification&ARIMA based forecasting of rainfall-temperature dynamics[C]//International Conference on Signal Processing and Communication,2016:490-495.
[4]Huang C Y,Liu Y W,Tzeng W C,et al.Short term wind speed predictions by using the grey prediction model based forecast method[C]//Green Technologies Conference.IEEE,2011:1-5.
[5]Jose C,Goyal P,Aggrwal P,et al.Local deep kernel learning for efficient non-linear SVM prediction[C]//International Conference on International Conference on Machine Learning.JMLR.org,2013:III-486.
[6]Venkadesh S,Hoogenboom G,Potter W,et al.A genetic algorithm to refine input data selection for air temperature prediction using artificial neural networks[J].Applied Soft Computing Journal,2013,13(5):2253-2260.
[7]ZHU Jingjing,ZHAO Xiaoping,WU Sheng’an,et al.Research on hainan air temperature prediction model based on support vector machine[J].Journal of Hainan University(Natural Science Edition),2016,34(1):40-44(in Chinese).[朱晶晶,赵小平,吴胜安,等.基于支持向量机的海南气温预测模型研究[J].海南大学学报(自然科学版),2016,34(1):40-44.]
[8]NIU Zhijuan,HU Hongping.Prediction model of monthly mean air temperature based on principal component analysis and BP neural network and RBF neural network[J].High School Science Journal,2015,35(11):6-8(in Chinese).[牛志娟,胡红萍.基于主成分分析的BP神经网络和RBF神经网络月平均气温预测模型[J].高师理科学刊,2015,35(11):6-8.]
[9]ZHOU Guobing.Recurrent neural network with minimal gate structure and its application[D].Nanjing:Nanjing University,2016(in Chinese).[周国兵.最少门结构的循环神经网络及其应用[D].南京:南京大学,2016.]
[10]CAO Yuhui.A study of text emotion analysis based on depth learning[D].Harbin:Harbin Institute of Technology,2016(in Chinese).[曹宇慧.基于深度学习的文本情感分析研究[D].哈尔滨:哈尔滨工业大学,2016.]
[11]LU Zenan,SHANG Yulin.Steel price forecast based on LSTM neural network model[J].Technology Horizon,2017(13):116-117(in Chinese).[陆泽楠,商玉林.基于LSTM神经网络模型的钢铁价格预测[J].科技视界,2017(13):116-117.]
[12]YAO Dengju,YANG Jing,ZHAN Xiaojuan.Feature selection algorithm based on random forest[J].Journal of Jilin University(Engineering),2014,44(1):137-141(in Chinese).[姚登举,杨静,詹晓娟.基于随机森林的特征选择算法[J].吉林大学学报(工),2014,44(1):137-141.]
[13]ZHOU Jianqiang,LI Yuna,QU Weidong,et al.Prediction of ultra-short term wind speed based on BP neural network and wind speed and space information[J].Power Grid and Clean Energy,2016,31(4):109-112(in Chinese).[周建强,李玉娜,屈卫东,等.基于风速时空信息的BP神经网络超短期风速预测研究[J].电网与清洁能源,2016,31(4):109-112.]
[14]WANG Huizhong,LIU Ke,ZHU Hongyi.Power system load forecasting based on cloud model and RBF support vector machine[J].Journal of Lanzhou University of Technology,2016,42(4):85-88(in Chinese).[王惠中,刘轲,朱宏毅.基于云模型RBF支持向量机的电力系统负荷预测[J].兰州理工大学学报,2016,42(4):85-88.]