Abstract
In recent years, more and more people have been plagued by respiratory diseases. The air quality, which is characterized by inhalable particles and fine particles, has attracted increasing attention. Accurately monitor and forecast the quality of air could not only help the government conduct interventions to alleviate the air pollution earlier, but also alert relevant people who suffer from respiratory diseases. In order to develop effective Air Quality Index (AQI) prediction models, this paper compared the performance of different Machine Learning (ML) methods and feature selection methods. First the air quality data in Beijing from 2016 to 2017 were collected. Then Multi-Linear Regression (MLR), Random forest Regression (RFR), BP Neural Network (BPNN) and Support Vector Regression (SVR) algorithm were trained on 10-fold cross validation. Correlation coefficient (R), mean absolute error (MAE) and root mean square error (RMSE) were used as evaluation metrics. The experimental results showed that the performance of SVR and BPNN were similarly well. MLR had the worst performance, which was possibly caused by a small feature dimension, and RFR had higher accuracy and better generalization capability than the other models, probably because the algorithm of regression tree in random forest included the interaction of variables.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yang, S.: Application of random forest algorithm in urban air quality prediction. Stat. Decis. 20, 83–86 (2017)
Keller, C.A., Evans, M.J.: Machine learning and air quality modeling. In: Big Data 2017, vol. 12, pp. 4570–4576. IEEE, Boston (2017)
Rita, R.: Institute for Health Metrics and Evaluation, WA. Lancet 389(10068), 493 (2017)
Guo, Q.: Prediction of atmospheric pollution based on neural network. Electron. Test 18, 75–76 (2015)
Zhang, M.: Urban air pollution forecasting method. Clim. Environ. Stud. 1, 113–118 (2001)
Wang, Q.: Existing problems and new ideas of current urban air pollution forecasting methods. Environ. Sci. Technol. 32(3), 189–192 (2009)
Yin, W.: Big data air pollution prediction based on deep learning. China Environ. Manage. 7(6), 46–52 (2015)
Xue, X.: Study on Qinling air quality prediction based on BP neural network. Xi’an University of Architecture and Technology (2014)
Wang, S.: The relationship between urban air quality and meteorological conditions and air quality forecast system. Meteorol. Technol. 6, 688–692 (2006)
Xu, L.: Partial correlation analysis of O3 and NO2 in Beijing Area. Urban Environ. Urban Ecol. 2, 67–71 (2013)
Jarauta-Bragulat, E.: Air Quality Index revisited from a compositional point of view. Math. Geosci. 48, 1–13 (2016)
Xu, X.: Combined multifractal analysis of PM2.5 trends. J. Hefei Univ. 24(3), 26–30 (2014)
Xu, M.: Analysis and prediction of AQI influence factors based on partial correlation and stepwise regression methods. Front. Environ. Prot. 3, 191–201 (2017)
Yang, J.J., Li, J., Shen, R.: Exploiting ensemble learning for automatic cataract detection and grading. Comput. Methods Programs Biomed. 124, 45–57 (2016)
Breiman, L.: Random forests. Statistics (Ber) 45(1), 1–33 (2001)
Cotter, A., Shamir, O., Srebro, N.: Better mini-batch algorithms via accelerated gradient methods. In: NIPS2011, vol. 24, pp. 1647–1655 (2011)
Wang, H.: Multivariate linear regression prediction modeling method. J. Beihang Univ. 4, 500–504 (2007)
Cotter, A., Shamir, O., Srebro N., Sridharan, K.: Better mini-batch algorithms via accelerated gradient methods. In: Conference on Neural Information Processing Systems, pp. 1647–1655 (2011)
John, S.H.: Prediction of Ozone formation based on neural network. Energy. ASCE 8, 688–696 (2000)
Alex, J.: A tutorial on support vector regression. Stat. Comput. 3, 199–222 (2014)
Li, X.: Analysis on the characteristics and influencing factors of air pollution index in China. Environ. Sci. 33(6), 1936–1943 (2014)
Jiao, W.: Correlation analysis and partial correlation analysis of the influence factors of gas daily load. Gas Heat 30(5), 1–5 (2010)
Singh, K.P.: Identifying pollution sources and predicting urban air quality using ensemble learning methods. Atmos. Environ. 80(6), 426–437 (2013)
Acknowledgements
This work is supported by National Natural Science Foundation of China (61702021), Beijing Natural Science Foundation (4174082), General Program of Science and Technology Plans of Beijing Education Committee (SQKM201710005021), Fundamental Research Foundation of Beijing University of Technology (PXM2017_014204_500087), and Funds of Beijing Advanced Innovation Center for Future Internet Technology of Beijing University of Technology (BJUT).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, B., Shi, C., Li, J., Li, Y., Lang, J., Gu, R. (2019). Comparison of Different Machine Learning Methods to Forecast Air Quality Index. In: Hung, J., Yen, N., Hui, L. (eds) Frontier Computing. FC 2018. Lecture Notes in Electrical Engineering, vol 542. Springer, Singapore. https://doi.org/10.1007/978-981-13-3648-5_27
Download citation
DOI: https://doi.org/10.1007/978-981-13-3648-5_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-3647-8
Online ISBN: 978-981-13-3648-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)