基于自编码网络的空气污染物浓度预测
|
摘要
深度学习为城市空气污染物浓度预测提供了更为强大的数据拟合能力,为空气污染预测提供全新的智能计算方法.为此,提出了一个基于自编码神经网络的污染物浓度预测模型AEPP(auto-encoder-based pollutant prediction).该模型包括编码器和解码器两个部分.其中,编码器用于提取出时间序列污染物浓度数据分布特征,即语境向量;解码器利用提取的特征预测未知时间内污染物浓度数据.模型中编码器和解码器采用多层LSTM(long short-term memory)模型结构,实现长时间依赖预测目标.实验表明,提出的模型可以提高对污染物浓度的预测水平.
In this paper, an autoencoder-based pollutant prediction(AEPP) model is proposed based on the auto-encoder neural network, which is composed of an encoder and a decoder. First, the encoder extracts the distribution characteristics of the time series of pollutant concentration data, namely the context vector. Secondly, the decoder uses the extracted characteristics to predict the pollutant concentration data in the next unknown time. Both the encoder and the decoder in the model can adopt several LSTM structures for long-time prediction. Experiments show that the AEPP model proposed in this paper can improve the effect of pollutant prediction.
In this paper, an autoencoder-based pollutant prediction(AEPP) model is proposed based on the auto-encoder neural network, which is composed of an encoder and a decoder. First, the encoder extracts the distribution characteristics of the time series of pollutant concentration data, namely the context vector. Secondly, the decoder uses the extracted characteristics to predict the pollutant concentration data in the next unknown time. Both the encoder and the decoder in the model can adopt several LSTM structures for long-time prediction. Experiments show that the AEPP model proposed in this paper can improve the effect of pollutant prediction.
引文
[1] 王俭,胡筱敏,郑龙熙,等.基于BP模型的大气污染预报方法的研究[J].环境科学研究,2002,15(5):62.WANG Jian,HU Xiaomin,ZHENG Longxi,et al.Study on forecasting of air pollution based on bp model[J].Research of Environmental Sciences,2002,15(5):62.
[2] HOSSAIN M,REKABDAR B,LOUIS S J,et al.Forecasting the weather of Nevada:a deep learning approach[C]//2015 International Joint Conference on Neural Networks (IJCNN).Killarney:IEEE,2015:1-6.
[3] ONG B T,SUGIURA K,ZETTSU K.Dynamic pre-training of deep recurrent neural networks for predicting environmental monitoring data[C]//IEEE International Conference on Big Data.Washington D C:IEEE Computer Society,2014:760-765.
[4] KUREMOTO T,KIMURA S,KOBAYASHI K,et al.Time series forecasting using a deep belief network with restricted Boltzmann machines[J].Neurocomputing,2014,137(15):47.
[5] LENDASSE A,OJA E,SIMULA O,et al.Time series prediction competition:the CATS benchmark[J].Neurocomputing,2007,70(13/14/15):2325.
[6] BOX G E P,JENKINS G M,REINSEL G C.Time series analysis:forecasting and control[M].5th ed.Hoboken N J:John Wiley & Sons,2015.
[7] 谢永华,张鸣敏,杨乐,等.基于支持向量机回归的城市PM2.5浓度预测[J].计算机工程与设计,2015(11):3106.XIE Yonghua,ZHANG Mingmin,YANG Le,et al.Predicting urban PM2.5 concentration in China using support vector regression[J].Computer Engineering and Design,2015(11):3106.
[8] 陈俏,曹根牛,陈柳.支持向量机应用于大气污染物浓度预测[J].计算机技术与发展,2010,20(1):250.CHEN Qiao,CAO Genniu,CHEN Liu.Application of support vector machine to atmospheric pollution prediction[J].Computer Technology and Development,2010,20(1):250.
[9] 黄思,唐晓,徐文帅,等.利用多模式集合和多元线性回归改进北京PM10预报[J].环境科学学报,2015,35(1):56.HUANG Si,TANG Xiao,XU Wenshuai,et al.Application of ensemble forecast and linear regression method in improving PM10 forecast over Beijing areas[J].Acta Scientiae Circumstantiae,2015,35(1):56.
[10] DENG L,LI X.Machine learning paradigms for speech recognition:an overview[J].IEEE Transactions on Audio Speech & Language Processing,2013,21(5):1060.
[11] DAN C,MEIER U,MASCI J,et al.Multi-column deep neural network for traffic sign classification[J].Neural Networks the Official Journal of the International Neural Network Society,2012,32(1):333.
[12] BALDI P,SADOWSKI P,WHITESON D.Searching for exotic particles in high-energy physics with deep learning.[J].Nature Communications,2014,5(5):4308.
[13] LANGE S,RIEDMILLER M.Deep auto-encoder neural networks in reinforcement learning[C]//International Joint Conference on Neural Networks (IJCNN).Barcelona:IEEE,2010:1-8.
[14] BALDI P.Autoencoders,unsupervised learning and deep architectures[C]//Proceedings of ICML workshop on unsupervised and transfer learning.Edinburgh:Journal of Machine Learning and Research,2012:37-49.
[15] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735.
[16] NOBLE W S.What is a support vector machine?[J].Nature Biotechnology,2006,24(12):1565.
[17] 罗瑜.支持向量机在机器学习中的应用研究[D].成都:西南交通大学,2007.LUO Yu.Research on application of support vector machine in machine learning[D].Chengdu:Southwest Jiaotong University,2007.
[18] 陈晓峰,王士同,曹苏群.自适应误差惩罚支撑向量回归机[J].电子与信息学报,2008,30(2):367.CHEN Xiaofeng,WANG Shitong,CAO Suqun.SVR with adaptive error penalization[J].Journal of Electronics & Information Technology,2008,30(2):367.
[19] DRAPER N R,SMITH H.Selecting the “best” regression equation[J].Applied Regression Analysis,1998(1):327.
[20] OSCAR E D Q.Deep learning for temperature prediction using GPUs[D].Valencia:Universitat Politècnica de València,2015.
[21] SERGIO A T,LUDERMIR T B.Deep learning for wind speed forecasting in northeastern region of Brazil[C]//Brazilian Conference on Intelligent Systems.Natal:IEEE,2015:322-327.
[22] 尹文君,张大伟,严京海,等.基于深度学习的大数据空气污染预报[J].中国环境管理,2015(6):46.YIN Wenjun,ZHANG Dawei,YAN Jinghai,et al.Deep learning based air pollutant forecasting with big data[J].Chinese Journal of Environmental Management,2015(6):46.
[23] HINTON G E.A practical guide to training restricted Boltzmann machines[J].Momentum,2010,9(1):599.
[24] KUMAR P R,RAVI V.Bankruptcy prediction in banks and firms via statistical and intelligent techniques-a review[J].European Journal of Operational Research,2007,180(1):1.
[25] DENG L,HINTON G,KINGSBURY B.New types of deep neural network learning for speech recognition and related applications:an overview[C]//2013 IEEE International Conference on Acoustics,Speech and Signal Processing.Vancouver:IEEE,2013:8599-8603.
[26] ATHIRA V,GEETHA P,VINAYAKUMAR R,et al.DeepAirNet:applying recurrent networks for air quality prediction[J].Procedia Computer Science,2018,132:1394.
[27] LIU X,LIU Q,ZOU Y,et al.A self-organizing LSTM-based approach to PM2.5 forecast[C]//International Conference on Cloud Computing and Security.Haikou:Springer,2018:683-693.
[28] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436.
[2] HOSSAIN M,REKABDAR B,LOUIS S J,et al.Forecasting the weather of Nevada:a deep learning approach[C]//2015 International Joint Conference on Neural Networks (IJCNN).Killarney:IEEE,2015:1-6.
[3] ONG B T,SUGIURA K,ZETTSU K.Dynamic pre-training of deep recurrent neural networks for predicting environmental monitoring data[C]//IEEE International Conference on Big Data.Washington D C:IEEE Computer Society,2014:760-765.
[4] KUREMOTO T,KIMURA S,KOBAYASHI K,et al.Time series forecasting using a deep belief network with restricted Boltzmann machines[J].Neurocomputing,2014,137(15):47.
[5] LENDASSE A,OJA E,SIMULA O,et al.Time series prediction competition:the CATS benchmark[J].Neurocomputing,2007,70(13/14/15):2325.
[6] BOX G E P,JENKINS G M,REINSEL G C.Time series analysis:forecasting and control[M].5th ed.Hoboken N J:John Wiley & Sons,2015.
[7] 谢永华,张鸣敏,杨乐,等.基于支持向量机回归的城市PM2.5浓度预测[J].计算机工程与设计,2015(11):3106.XIE Yonghua,ZHANG Mingmin,YANG Le,et al.Predicting urban PM2.5 concentration in China using support vector regression[J].Computer Engineering and Design,2015(11):3106.
[8] 陈俏,曹根牛,陈柳.支持向量机应用于大气污染物浓度预测[J].计算机技术与发展,2010,20(1):250.CHEN Qiao,CAO Genniu,CHEN Liu.Application of support vector machine to atmospheric pollution prediction[J].Computer Technology and Development,2010,20(1):250.
[9] 黄思,唐晓,徐文帅,等.利用多模式集合和多元线性回归改进北京PM10预报[J].环境科学学报,2015,35(1):56.HUANG Si,TANG Xiao,XU Wenshuai,et al.Application of ensemble forecast and linear regression method in improving PM10 forecast over Beijing areas[J].Acta Scientiae Circumstantiae,2015,35(1):56.
[10] DENG L,LI X.Machine learning paradigms for speech recognition:an overview[J].IEEE Transactions on Audio Speech & Language Processing,2013,21(5):1060.
[11] DAN C,MEIER U,MASCI J,et al.Multi-column deep neural network for traffic sign classification[J].Neural Networks the Official Journal of the International Neural Network Society,2012,32(1):333.
[12] BALDI P,SADOWSKI P,WHITESON D.Searching for exotic particles in high-energy physics with deep learning.[J].Nature Communications,2014,5(5):4308.
[13] LANGE S,RIEDMILLER M.Deep auto-encoder neural networks in reinforcement learning[C]//International Joint Conference on Neural Networks (IJCNN).Barcelona:IEEE,2010:1-8.
[14] BALDI P.Autoencoders,unsupervised learning and deep architectures[C]//Proceedings of ICML workshop on unsupervised and transfer learning.Edinburgh:Journal of Machine Learning and Research,2012:37-49.
[15] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735.
[16] NOBLE W S.What is a support vector machine?[J].Nature Biotechnology,2006,24(12):1565.
[17] 罗瑜.支持向量机在机器学习中的应用研究[D].成都:西南交通大学,2007.LUO Yu.Research on application of support vector machine in machine learning[D].Chengdu:Southwest Jiaotong University,2007.
[18] 陈晓峰,王士同,曹苏群.自适应误差惩罚支撑向量回归机[J].电子与信息学报,2008,30(2):367.CHEN Xiaofeng,WANG Shitong,CAO Suqun.SVR with adaptive error penalization[J].Journal of Electronics & Information Technology,2008,30(2):367.
[19] DRAPER N R,SMITH H.Selecting the “best” regression equation[J].Applied Regression Analysis,1998(1):327.
[20] OSCAR E D Q.Deep learning for temperature prediction using GPUs[D].Valencia:Universitat Politècnica de València,2015.
[21] SERGIO A T,LUDERMIR T B.Deep learning for wind speed forecasting in northeastern region of Brazil[C]//Brazilian Conference on Intelligent Systems.Natal:IEEE,2015:322-327.
[22] 尹文君,张大伟,严京海,等.基于深度学习的大数据空气污染预报[J].中国环境管理,2015(6):46.YIN Wenjun,ZHANG Dawei,YAN Jinghai,et al.Deep learning based air pollutant forecasting with big data[J].Chinese Journal of Environmental Management,2015(6):46.
[23] HINTON G E.A practical guide to training restricted Boltzmann machines[J].Momentum,2010,9(1):599.
[24] KUMAR P R,RAVI V.Bankruptcy prediction in banks and firms via statistical and intelligent techniques-a review[J].European Journal of Operational Research,2007,180(1):1.
[25] DENG L,HINTON G,KINGSBURY B.New types of deep neural network learning for speech recognition and related applications:an overview[C]//2013 IEEE International Conference on Acoustics,Speech and Signal Processing.Vancouver:IEEE,2013:8599-8603.
[26] ATHIRA V,GEETHA P,VINAYAKUMAR R,et al.DeepAirNet:applying recurrent networks for air quality prediction[J].Procedia Computer Science,2018,132:1394.
[27] LIU X,LIU Q,ZOU Y,et al.A self-organizing LSTM-based approach to PM2.5 forecast[C]//International Conference on Cloud Computing and Security.Haikou:Springer,2018:683-693.
[28] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436.
© 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 |