A comparative study of different LSTM neural networks in predicting air pollutant concentrations

Preeti Bamane; Mangal Patil

doi:10.17485/IJST/v13i35.1276

Article

A comparative study of different LSTM neural networks in predicting air pollutant concentrations

VIEWS 1811
PDF 459

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v13i35.1276

Year: 2020, Volume: 13, Issue: 35, Pages: 3664-3674

Original Article

A comparative study of different LSTM neural networks in predicting air pollutant concentrations

Preeti Bamane^1*, Mangal Patil²

¹PG Scholar, Dept. of Electronics, Bharati Vidyapeeth Deemed to be University College of Engineering, Pune, Maharashtra, India
²Assistant Professor, Dept. of Electronics, Bharati Vidyapeeth Deemed to be University College of Engineering, Pune, Maharashtra, India

*Corresponding Author
Email: [email protected]

Received Date:08 August 2020, Accepted Date:30 August 2020, Published Date:05 October 2020

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Aim/Objective: This study aims to identify the key trends among different types of LSTM networks and their performance and usage for air pollutants(PM2:5 and PM10) concentrations prediction. Methods: In this study, the extensive research efforts were made for Particulate Matters (i.e., PM10 and PM2:5) prediction using several LSTM networks, namely Vanilla, Stacked, and Bidirectional. These are trained and tested using air quality data, retrieved from the Central Pollution Control Board (CPCB) of the town Bawana, Delhi. Realtime hourly a data from 2018 to 2020 with nine air pollutants are considered for experimental analysis. We conducted data preparation strategy to select the best features, which improve the quality of the data. An adequate number of experiments are conducted to choose the best hyperparameters using Python package TensorFlow. Findings: MSE, MAE, RMSE, and R2 parameters are used as the statistical criteria for evaluating the model’s performances.The numerical experiments revealed that deep neural networks could predict the Particulate Matters (mg/m3) with high accuracy. We found that Stacked LSTM with minimum MSE, MAE, RMSE, and maximum R2 works better than the other two methods, i.e., Vanilla LSTM and Bidirectional LSTM for PM2:5 and PM10 concentrations prediction. The empirical, experimental analysis also shows that Vanilla, Stacked, and Bidirectional LSTM models have comparatively minimum MSE, MAE, RMSE, and maximum R2 for PM2:5 than PM10 concentration prediction. Applications: With the help of a predictive model, one can find reliable fine concentration prediction information for a particular area. The resultant information on relative performance can help researchers in the selection of an appropriate LSTM algorithm for their studies.

Keywords: Air pollutants; air quality index; PM concentrations; LSTM;TensorFlow; air pollution

References

Chatterjee P. India takes steps to curb air pollution. Bulletin of the World Health Organization. 2016;94(7):481–556. Available from: http://dx.doi.org/10.2471/BLT.16.020716
Patel P. Tackling Delhi’s Air Pollution Problem. ACS Cent. Sci. 2019;5:3–6. Available from: https://doi.org/10.1021/acscentsci.9b00009
Pant P, Lal MR, Guttikunda KS, Russell GA, Nagpure SA, Ramaswami A, et al. Monitoring particulate matter in India: recent trends and future outlook. Air Quality, Atmosphere & Health. 2019;12(1):45–58. Available from: https://dx.doi.org/10.1007/s11869-018-0629-6
Harsh M, Khushboo J. Air Pollution Problem in Delhi. Journal of Critical Reviews. 2020;7(10):723–727.
Chaudhary V, Deshbhratar A, Kumar V, Paul D. Time series based LSTM model to predict air pollutant’s concentration for prominent cities in India. 2018.
Tsai Y, Zeng Y, Chang Y. Air Pollution Forecasting Using RNN with LSTM. IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress. 2018;p. 1074–1079. Available from: https://doi.org/10.1109/DASC/PiCom/DataCom/CyberSciTec.2018.00178
Navares R, Aznarte LJ. Predicting air quality with deep learning LSTM: Towards comprehensive models. Ecological Informatics. 2020;55. Available from: https://dx.doi.org/10.1016/j.ecoinf.2019.101019
Rao KS, Devi GL, Ramesh N. Air Quality Prediction in Visakhapatnam with LSTM based Recurrent Neural Networks. International Journal of Intelligent Systems and Applications. 2019;11(2):18–24. Available from: https://dx.doi.org/10.5815/ijisa.2019.02.03
Jiao Y, Wang Z, Zhang Y. Prediction of Air Quality Index Based on LSTM. In: IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). (pp. 17-20) 2019.
Athira V, Geetha P, Vinayakumar R, Soman KP. DeepAirNet: Applying Recurrent Networks for Air Quality Prediction. Procedia Computer Science. 2018;132:1394–1403. Available from: https://dx.doi.org/10.1016/j.procs.2018.05.068
Verma I, Ahuja R, Meisheri H, Dey L. Air Pollutant Severity Prediction Using Bi-Directional LSTM Network. ACM International Conference on Web Intelligence (WI). 2018;p. 651–654. Available from: https://doi.org/10.1109/WI.2018.00-19
Tong W, Li L, Zhou X, Hamilton A, Zhang K. Deep learning PM2.5 concentrations with bidirectional LSTM RNN. Air Quality, Atmosphere & Health. 2019;12(4):411–423. Available from: https://dx.doi.org/10.1007/s11869-018-0647-4
Bui TC, Le VD, Cha SK. A deep learning approach for forecasting air pollution in South Korea using LSTM. 2018. Available from: http://www.arxiv.org/abs/1804.07891v3
Xayasouk T, Lee H, Lee G. Air Pollution Prediction Using Long Short-Term Memory (LSTM) and Deep Autoencoder (DAE) Models. Sustainability. 2020;12. Available from: https://dx.doi.org/10.3390/su12062570
Qiu Z. Quantitative Testing of micro-cracks by the MFL technique Based on GA-BP neural network. International Journal of Manufacturing Research. 2017;12. Available from: https://dx.doi.org/10.1504/ijmr.2017.10005448
Li X, Peng L, Yao X. Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation. Environmental pollution. 2017;231:997–1004. Available from: https://doi.org/10.1016/j.envpol.2017.08.114
Indian government, Central Pollution Control Board (CPCB) Available from: https://data.gov.in/catalog/historical-daily-ambient-air-quality-data (accessed 2020-07-05)
Dhankhar K, Solanki. A comprehensive review of tools and techniques for big data analysis. International Journal of Emerging Trends in Engineering Research. 2019;7(11):556–562. Available from: https://doi.org/10.30534/ijeter/2019/257112019
Chang JC, Hanna SR. Air quality model performance evaluation. Meteorology and Atmospheric Physics. 2004;87(1-3):167–196. Available from: https://dx.doi.org/10.1007/s00703-003-0070-7
Mcdonald JH. Handbook of Biological Statistics. Baltimore, MD. Sparky House Publishing. 2009.
Cohen J, Cohen P, West SG, Aiken LS. Applied Multiple Regression/Correlation Analysis for the Behavioral Sciences, Routledge. 2013. Available from: https://doi.org/10.4324/9780203774441
FelixGers A, Schmidhuber J, Cummins F. Learning to Forget: Continual Prediction with LSTM. Neural Computation. 2000;12(10):2451–2471. Available from: https://dx.doi.org/10.1162/089976600300015015
Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Computation. 1997;9(8):1735–1780. Available from: https://dx.doi.org/10.1162/neco.1997.9.8.1735
Dozat T. Incorporating Nesterov momentum into Adam. Learning Representations . 2016.

Copyright

© 2020 Bamane & Patil.This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee).