A Deep Belief Network Based Model for Urban Haze Prediction

In order to improve the accuracy of urban haze prediction, a novel deep belief network (DBN)-based model was proposed. Firstly, data pertaining to both air quality and the environment (e.g. meteorology) data was monitored and collected. The primary haze influencing elements were discovered by analyzing the correlations between each of the meteorological factors and haze. Secondly, a DBN combined with multilayer restricted Boltzmann machines and a single-layer back propagation network was applied. Thirdly, the meteorological data predictions were carried out by using a competitive adaptive-reweighed method. A stable model was established by big-data training and its accuracy was verified by experiments. Results demonstrate that the pollution haze occurs in accordance with regular laws, and is greatly affected by wind direction, atmospheric pressure, and seasons. The correlation coefficient (CC) between the actual haze value and the prediction of the proposed model is 0.8, and the mean absolute error (MAE) is 26 μg/m3. Compared with the traditional prediction algorithms, the CC is improved by 18 % on average, while the MAE is reduced by 15.7 μg/m3. The proposed method has a good prospect to predict haze and investigate the main causes of it. This study provides data support for urban haze prevention and governance.

[1]  J. Kukkonen,et al.  Intercomparison of air quality data using principal component analysis, and forecasting of PM₁₀ and PM₂.₅ concentrations using artificial neural networks, in Thessaloniki and Helsinki. , 2011, The Science of the total environment.

[2]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[3]  Shikha Gupta,et al.  Linear and nonlinear modeling approaches for urban air quality prediction. , 2012, The Science of the total environment.

[4]  Jihoon Yang,et al.  Indoor Air Quality Analysis Using Deep Learning with Sensor Data , 2017, Sensors.

[5]  Saeid Baroutian,et al.  Forecasting Extreme PM10 Concentrations Using Artificial Neural Networks , 2012 .

[6]  N. Pérez,et al.  Neural network model for the prediction of PM10 daily concentrations in two sites in the Western Mediterranean. , 2013, The Science of the total environment.

[7]  R. Muller,et al.  Air Pollution in China: Mapping of Concentrations and Sources , 2015, PloS one.

[8]  Xiang Li,et al.  Deep learning architecture for air quality predictions , 2016, Environmental Science and Pollution Research.

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

[10]  Lu Huimin,et al.  Translation Registration Algorithm for Multi - source Time Series Data Based on the Sliding Window , 2016 .

[11]  Giorgio Corani,et al.  Air quality prediction in Milan: feed-forward neural networks, pruned neural networks and lazy learning , 2005 .

[12]  Huiping Peng,et al.  Air quality prediction by machine learning methods , 2015 .

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

[14]  Pedro G. Lind,et al.  Air quality prediction using optimal neural networks with stochastic variables , 2013, 1307.3134.