Forecasting of ozone concentration in smart city using deep learning

Clean air is one of the most important needs for the well-being of human being health. In smart cities, timely and precise air pollution levels knowledge is vital for the successful setup of smart pollution systems. Recently, pollution and weather data in smart city have been bursting, and we have truly got into the era of big data. Ozone is considered as one of the most air pollutants with hurtful impact to human health. Existing methods used to predict the level of ozone uses shallow pollution prediction models and are still unsatisfactory in their accuracy to be used in many real-world applications. In order to increase the accuracy of prediction models we come up with the concept of using deep architecture models tested on big pollution and weather data. In this paper, a new deep learning-based ozone level prediction model is proposed, which considers the pollution and weather correlations integrally. This deep learning model is used to learn ozone level features, and it is trained using a grid search technique. A deep architecture model is utilized to represent ozone level features for prediction. Moreover, experiments demonstrate that the proposed method for ozone level prediction has superior performance. The outcome of this study can be helpful in predicting the ozone level pollution in Aarhus city as a model of smart cities for improving accuracy of ozone forecasting tools.

[1]  Francisco Herrera,et al.  A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[2]  Albert Y. Zomaya,et al.  A Review of Ensemble Methods in Bioinformatics , 2010, Current Bioinformatics.

[3]  Krzysztof Siwek,et al.  Improving the accuracy of prediction of PM10 pollution by the wavelet transformation and an ensemble of neural predictors , 2012, Eng. Appl. Artif. Intell..

[4]  T Fontes,et al.  Can artificial neural networks be used to predict the origin of ozone episodes? , 2014, The Science of the total environment.

[5]  K. Tsui,et al.  Imbalanced classification by learning hidden data structure , 2016 .

[6]  Bing Yi,et al.  Predicting reaction rate constants of ozone with organic compounds from radical structures , 2012 .

[7]  A. Comrie.  Comparing Neural Networks and Regression Models for Ozone Forecasting , 1997 .

[8]  Nitesh V. Chawla,et al.  Editorial: special issue on learning from imbalanced data sets , 2004, SKDD.

[9]  Joaquín B. Ordieres Meré,et al.  Development and comparative analysis of tropospheric ozone prediction models using linear and artificial intelligence-based models in Mexicali, Baja California (Mexico) and Calexico, California (US) , 2008, Environ. Model. Softw..

[10]  Andreja Stojić,et al.  Forecasting of VOC emissions from traffic and industry using classification and regression multivariate methods. , 2015, The Science of the total environment.

[11]  K. Wilson,et al.  Linear stochastic models for forecasting daily maxima and hourly concentrations of air pollutants , 1975 .

[12]  Yang Zhang,et al.  Real-time air quality forecasting, part I: History, techniques, and current status , 2012 .

[13]  Sancho Salcedo-Sanz,et al.  Prediction of hourly O3 concentrations using support vector regression algorithms , 2010 .

[14]  Surajit Chattopadhyay,et al.  Artificial neural network with backpropagation learning to predict mean monthly total ozone in Arosa, Switzerland , 2007 .

[15]  Andrew K. C. Wong,et al.  Classification of Imbalanced Data: a Review , 2009, Int. J. Pattern Recognit. Artif. Intell..

[16]  Shikha Gupta,et al.  Identifying pollution sources and predicting urban air quality using ensemble learning methods , 2013 .

[17]  Dezhi Sun,et al.  Ozone concentration forecast method based on genetic algorithm optimized back propagation neural networks and support vector machine data classification , 2011 .

[18]  Li-Chiu Chang,et al.  Forecasting of ozone episode days by cost-sensitive neural network methods. , 2009, The Science of the total environment.

[19]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

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

[21]  Wenjian Wang,et al.  Online prediction model based on support vector machine , 2008, Neurocomputing.

[22]  Francisco Herrera,et al.  Analysis of preprocessing vs. cost-sensitive learning for imbalanced classification. Open problems on intrinsic data characteristics , 2012, Expert Syst. Appl..

[23]  Kun Zhang,et al.  Forecasting skewed biased stochastic ozone days: analyses, solutions and beyond , 2008, Knowledge and Information Systems.

[24]  Gavin C. Cawley,et al.  Statistical models to assess the health effects and to forecast ground-level ozone , 2006, Environ. Model. Softw..

[25]  Scott M. Robeson,et al.  Evaluation and comparison of statistical forecast models for daily maximum ozone concentrations , 1990 .

[26]  Derya Birant.  Comparison of Decision Tree Algorithms for Predicting Potential Air Pollutant Emissions with Data Mining Models , 2011 .

[27]  Vivien Mallet,et al.  Ensemble forecasting with machine learning algorithms for ozone, nitrogen dioxide and PM10 on the Prev'Air platform , 2014 .

[28]  Wei-Zhen Lu,et al.  Ground-level ozone prediction by support vector machine approach with a cost-sensitive classification scheme. , 2008, The Science of the total environment.

[29]  Sergio Machado Corrêa,et al.  Prediction of ozone concentration in tropospheric levels using artificial neural networks and support vector machine at Rio de Janeiro, Brazil , 2014 .

[30]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[31]  Andrea L. Pineda Rojas.  Simple atmospheric dispersion model to estimate hourly ground-level nitrogen dioxide and ozone concentrations at urban scale , 2014, Environ. Model. Softw..