Deep learning architecture for air quality predictions

With the rapid development of urbanization and industrialization, many developing countries are suffering from heavy air pollution. Governments and citizens have expressed increasing concern regarding air pollution because it affects human health and sustainable development worldwide. Current air quality prediction methods mainly use shallow models; however, these methods produce unsatisfactory results, which inspired us to investigate methods of predicting air quality based on deep architecture models. In this paper, a novel spatiotemporal deep learning (STDL)-based air quality prediction method that inherently considers spatial and temporal correlations is proposed. A stacked autoencoder (SAE) model is used to extract inherent air quality features, and it is trained in a greedy layer-wise manner. Compared with traditional time series prediction models, our model can predict the air quality of all stations simultaneously and shows the temporal stability in all seasons. Moreover, a comparison with the spatiotemporal artificial neural network (STANN), auto regression moving average (ARMA), and support vector regression (SVR) models demonstrates that the proposed method of performing air quality predictions has a superior performance.

[1]  Jiwen Lu,et al.  PCANet: A Simple Deep Learning Baseline for Image Classification? , 2014, IEEE Transactions on Image Processing.

[2]  C. L. Philip Chen,et al.  Predictive Deep Boltzmann Machine for Multiperiod Wind Speed Forecasting , 2015, IEEE Transactions on Sustainable Energy.

[3]  N Künzli,et al.  Public-health impact of outdoor and traffic-related air pollution: a European assessment , 2000, The Lancet.

[4]  P. J. García Nieto,et al.  A SVM-based regression model to study the air quality at local scale in Oviedo urban area (Northern Spain): A case study , 2013, Appl. Math. Comput..

[5]  Nanda Kambhatla,et al.  Dimension Reduction by Local Principal Component Analysis , 1997, Neural Computation.

[6]  Yu Zheng,et al.  U-Air: when urban air quality inference meets big data , 2013, KDD.

[7]  Ayse Betül Oktay,et al.  Forecasting air pollutant indicator levels with geographic models 3 days in advance using neural networks , 2010, Expert Syst. Appl..

[8]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.

[9]  Ajith Kaduwela,et al.  Seasonal modeling of PM2.5 in California's San Joaquin Valley , 2014 .

[10]  Victor R. Prybutok,et al.  Comparison of neural network models with ARIMA and regression models for prediction of Houston's daily maximum ozone concentrations , 2000, Eur. J. Oper. Res..

[11]  Alma Hodzic,et al.  A model inter-comparison study focussing on episodes with elevated PM10 concentrations , 2008 .

[12]  R. Burnett,et al.  Spatial Analysis of Air Pollution and Mortality in Los Angeles , 2005, Epidemiology.

[13]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[14]  Rita H. Wouhaybi,et al.  Comparison of neural networks for speaker recognition , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).

[15]  Marc'Aurelio Ranzato,et al.  Efficient Learning of Sparse Representations with an Energy-Based Model , 2006, NIPS.

[16]  J. Hooyberghs,et al.  A neural network forecast for daily average PM10 concentrations in Belgium , 2005 .

[17]  Tara N. Sainath,et al.  Deep Belief Networks using discriminative features for phone recognition , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  A. Osses,et al.  Forecasting urban PM10 and PM2.5 pollution episodes in very stable nocturnal conditions and complex terrain using WRF–Chem CO tracer model , 2011 .

[19]  Philippe Thunis,et al.  Evaluation and intercomparison of Ozone and PM10 simulations by several chemistry transport models over four European cities within the CityDelta project , 2007 .

[20]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[21]  Michelle L Bell,et al.  Spatial Heterogeneity of PM10 and O3 in São Paulo, Brazil, and Implications for Human Health Studies , 2011, Journal of the Air & Waste Management Association.

[22]  J. Chow,et al.  A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile , 2008 .

[23]  A. Clappier,et al.  Towards improving the simulation of meteorological fields in urban areas through updated/advanced surface fluxes description , 2008 .

[24]  Mastering the game of Go from scratch , 2018 .

[25]  F. J. D. C. Juez,et al.  Forecasting SO 2 Pollution Incidents by means of Elman Artificial Neural Networks and ARIMA Models , 2013 .

[26]  P. J. García Nieto,et al.  Nonlinear Air Quality Modeling Using Support Vector Machines in Gijón Urban Area (Northern Spain) at Local Scale , 2013 .

[27]  Etienne Barnard,et al.  Optimization for training neural nets , 1992, IEEE Trans. Neural Networks.

[28]  Michel Gerboles,et al.  Temporal trends of spatial correlation within the PM10 time series of the AirBase ambient air quality database , 2015 .

[29]  P. Goyal,et al.  Statistical models for the prediction of respirable suspended particulate matter in urban cities , 2006 .

[30]  Can Li,et al.  A study on the potential applications of satellite data in air quality monitoring and forecasting , 2011 .

[31]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[32]  Bindhu Lal,et al.  Prediction of dust concentration in open cast coal mine using artificial neural network , 2012 .

[33]  Daniel Jachyra,et al.  Neural Network Structure for Spatio-Temporal Long-Term Memory , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[34]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[35]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[36]  Runhe Shi,et al.  Ensemble and enhanced PM10 concentration forecast model based on stepwise regression and wavelet analysis , 2013 .

[37]  Yunhee Kim,et al.  Improving ozone modeling in complex terrain at a fine grid resolution: Part I – examination of analysis nudging and all PBL schemes associated with LSMs in meteorological model , 2010 .

[38]  T. Cheng,et al.  The Support Vector Machine for Nonlinear Spatio-Temporal Regression , 2007 .

[39]  Jung-Hun Woo,et al.  Source contributions to carbonaceous aerosol concentrations in Korea , 2011 .

[40]  Qi Wang,et al.  Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[41]  J. Oeppen.  The identification of regional forecasting models using space-time correlation , 1975 .

[42]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[43]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[44]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[45]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[46]  P. Legendre.  Spatial Autocorrelation: Trouble or New Paradigm? , 1993 .

[47]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[48]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[49]  Carlie J. Coats,et al.  High Performance Algorithms In The Sparse Matrix Operator Kernel Emissions (smoke) Modeling System , 1996 .

[50]  Marc'Aurelio Ranzato,et al.  Sparse Feature Learning for Deep Belief Networks , 2007, NIPS.

[51]  Ewout W. Steyerberg.  Statistical Models for Prediction , 2009 .

[52]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[53]  Petr Hájek,et al.  Ozone prediction on the basis of neural networks, support vector regression and methods with uncertainty , 2012, Ecol. Informatics.

[54]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .