Air quality modelling using long short-term memory (LSTM) over NCT-Delhi, India

  • Mrigank Krishan
  • Srinidhi Jha
  • Jew DasEmail author
  • Avantika Singh
  • Manish Kumar Goyal
  • Chandrra Sekar


Nowadays, monitoring and prediction of air quality parameters are becoming significantly important research topics in the context of increasing urbanization and industrialization. Therefore, efficient modelling of air quality parameters is essential because such an approach would enable to identify the existing and forthcoming implication of air pollution. In recent years, sharp rise in air pollution levels in Indian National Capital Territory of Delhi (NCT-Delhi) has made it the most polluted city of the world. Machine learning approaches are considered as an efficient and cost-effective method to model the air quality parameters and are widely used. However, current methods fail to incorporate long-term dependencies arising due to complex interaction of natural and anthropogenic factors. The present study is mainly aimed at predicting O3, PM2.5, NOx, and CO concentrations at a location in NCT-Delhi using the long short-term memory (LSTM) approach, which is considered as more efficient over other deep learning methods. Factors and parameters such as vehicular emissions, meteorological conditions, traffic data, and pollutant levels are employed in five different combinations. Performance evaluation of LSTM algorithms for hourly concentration prediction is carried out during 2008–2010, and it is found that LSTM models efficiently deal with the complexities and is immensely effective in ambient air quality forecasting. This paper can be considered as a significant motivation for carrying research on urban air pollution using latest LSTMs and helping the government and policymakers a better forecasting methodology for planning measures to curb ill impacts of degrading air quality.


Air pollution Machine learning Deep learning LSTM NCT-Delhi 



We thank the editor and two anonymous reviewers for their insightful and constructive comments to improve the manuscript significantly.


  1. Ahn J, Shin D, Kim K, Yang J (2017) Indoor air quality analysis using deep learning with sensor data. Sensors 17:2476CrossRefGoogle Scholar
  2. Almaraz M, Bai E, Wang C, Trousdell J, Conley S, Faloona I, Houlton BZ (2018) Agriculture is a major source of NOx pollution in California. Sci Adv 4:eaao3477. CrossRefGoogle Scholar
  3. Athanasiadis IN, Kaburlasos VG, Mitkas PA, Petridis V (2003) Applying machine learning techniques on air quality data for real-time decision support. In: First international NAISO symposium on information technologies in environmental engineering (ITEE’2003), Gdansk, Poland. CiteseerGoogle Scholar
  4. Automotive Research Association of India (2007) Air quality monitoring project-Indian clean air programme (ICAP). Draft Rep. on emission factor development for Indian vehicles, PuneGoogle Scholar
  5. Bao W, Yue J, Rao Y (2017) A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PLoS One 12:e0180944CrossRefGoogle Scholar
  6. Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5:157–166CrossRefGoogle Scholar
  7. Briggs DJ, de Hoogh C, Gulliver J, Wills J, Elliott P, Kingham S, Smallbone K (2000) A regression-based method for mapping traffic-related air pollution: application and testing in four contrasting urban environments. Sci Total Environ 253:151–167. CrossRefGoogle Scholar
  8. Chugh S, Kumar P, Muralidharan M, et al (2012) Development of Delhi driving cycle: a tool for realistic assessment of exhaust emissions from passenger cars in Delhi. SAE Technical PaperGoogle Scholar
  9. Fan J, Li Q, Hou J et al (2017) A spatiotemporal prediction framework for air pollution based on deep RNN. ISPRS Ann Photogramm Remote Sens Spat Inf Sci 4:15CrossRefGoogle Scholar
  10. Fu M, Wang W, Le Z, Khorram MS (2015) Prediction of particular matter concentrations by developed feed-forward neural network with rolling mechanism and gray model. Neural Comput & Applic 26:1789–1797CrossRefGoogle Scholar
  11. Ghasemi A, Amanollahi J (2019) Integration of ANFIS model and forward selection method for air quality forecasting. Air Qual Atmos Health 12:59–72. CrossRefGoogle Scholar
  12. Gokhale S, Pandian S (2007) A semi-empirical box modeling approach for predicting the carbon monoxide concentrations at an urban traffic intersection. Atmos Environ 41:7940–7950CrossRefGoogle Scholar
  13. Graves A, Mohamed A, Hinton G (2013) Speech recognition with deep recurrent neural networks. In: Acoustics, speech and signal processing (icassp), 2013 IEEE international conference on. IEEE, pp 6645–6649Google Scholar
  14. Gurjar BR, Ravindra K, Nagpure AS (2016) Air pollution trends over Indian megacities and their local-to-global implications. Atmos Environ 142:475–495CrossRefGoogle Scholar
  15. Gurjar BR, Van Aardenne JA, Lelieveld J, Mohan M (2004) Emission estimates and trends (1990–2000) for megacity Delhi and implications. Atmos Environ 38:5663–5681CrossRefGoogle Scholar
  16. Guttikunda SK, Calori G (2013) A GIS based emissions inventory at 1 km × 1 km spatial resolution for air pollution analysis in Delhi, India. Atmos Environ 67:101–111CrossRefGoogle Scholar
  17. Guttikunda SK, Goel R, Pant P (2014) Nature of air pollution, emission sources, and management in the Indian cities. Atmos Environ 95:501–510. CrossRefGoogle Scholar
  18. Guttikunda SK, Gurjar BR (2012) Role of meteorology in seasonality of air pollution in megacity Delhi, India. Environ Monit Assess 184:3199–3211CrossRefGoogle Scholar
  19. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780CrossRefGoogle Scholar
  20. PressTrust of India (2018) 40 pc of India’s population likely to reside in cities by 2030: Puri. Press Trust India, India TodayGoogle Scholar
  21. Jain S, Khare M (2010) Adaptive neuro-fuzzy modeling for prediction of ambient CO concentration at urban intersections and roadways. Air Qual Atmos Health 3:203–212. CrossRefGoogle Scholar
  22. Kalapanidas E, Avouris N (2001) Short-term air quality prediction using a case-based classifier. Environ Model Softw 16:263–272CrossRefGoogle Scholar
  23. Kim MH, Kim YS, Lim J, Kim JT, Sung SW, Yoo CK (2010) Data-driven prediction model of indoor air quality in an underground space. Korean J Chem Eng 27:1675–1680CrossRefGoogle Scholar
  24. Kurt A, Oktay AB (2010) Forecasting air pollutant indicator levels with geographic models 3 days in advance using neural networks. Expert Syst Appl 37:7986–7992CrossRefGoogle Scholar
  25. Legates DR, McCabe GJ Jr (1999) Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation. Water Resour Res 35:233–241CrossRefGoogle Scholar
  26. Li X, Peng L, Yao X, Cui S, Hu Y, You C, Chi T (2017) Long short-term memory neural network for air pollutant concentration predictions: method development and evaluation. Environ Pollut 231:997–1004CrossRefGoogle Scholar
  27. Mallet V, Sportisse B (2008) Air quality modeling: from deterministic to stochastic approaches. Comput Math Appl 55:2329–2337CrossRefGoogle Scholar
  28. Mayer H, Gomez F, Wierstra D, Nagy I, Knoll A, Schmidhuber J (2008) A system for robotic heart surgery that learns to tie knots using recurrent neural networks. Adv Robot 22:1521–1537CrossRefGoogle Scholar
  29. Mikolov T, Joulin A, Chopra S, Mathieu M, Ranzato MA (2014) Learning longer memory in recurrent neural networks. arXiv preprint arXiv:1412.7753Google Scholar
  30. Milionis AE, Davies TD (1994) Regression and stochastic models for air pollution—I. Review, comments and suggestions. Atmos Environ 28:2801–2810CrossRefGoogle Scholar
  31. Ni XY, Huang H, Du WP (2017) Relevance analysis and short-term prediction of PM2. 5 concentrations in Beijing based on multi-source data. Atmos Environ 150:146–161CrossRefGoogle Scholar
  32. Pardo E, Malpica N (2017) Air quality forecasting in Madrid using long short-term memory networks. In: International Work-Conference on the Interplay Between Natural and Artificial Computation. Springer, pp 232–239Google Scholar
  33. PTI (2018). 40 pc of India’s population likely to reside in cities by 2030: Puri. Press Trust India, India Today.Google Scholar
  34. Schnelle KB, Dey PR (2000) Atmospheric dispersion modeling compliance guide. McGraw-Hill, New YorkGoogle Scholar
  35. Sekar C, Gurjar BR, Ojha CSP, Goyal MK (2016a) Potential assessment of neural network and decision tree algorithms for forecasting ambient PM2.5 and CO concentrations: case study. J Hazard Toxic Radioact Waste 20:A5015001. CrossRefGoogle Scholar
  36. Sekar C, Ojha CSP, Gurjar BR, Goyal MK (2016b) Modeling and prediction of hourly ambient ozone (O3) and oxides of nitrogen (NOx) concentrations using artificial neural network and decision tree algorithms for an urban intersection in India. J Hazard Toxic Radioact Waste 20:A4015001. CrossRefGoogle Scholar
  37. Sønderby SK, Sønderby CK, Nielsen H, Winther O (2015) Convolutional LSTM networks for subcellular localization of proteins. In: International Conference on Algorithms for Computational Biology. Springer, pp 68–80Google Scholar
  38. Srivastava A, Jain VK (2005) A study to characterize the influence of outdoor SPM and associated metals on indoor environment in Delhi. J Environ Sci Eng 47:222–231Google Scholar
  39. UN (2018) 2018 revision of world urbanization prospects. Accessed 14 April 2019
  40. West JJ, Naik V, Horowitz LW, Fiore AM (2009) Effect of regional precursor emission controls on long-range ozone transport—part 1: short-term changes in ozone air quality. Atmos Chem Phys 9:6077–6093CrossRefGoogle Scholar
  41. WHO, 2018. Global Ambient Air Quality Database (update 2018). World Health Orgination.Google Scholar
  42. Zhang J, Zhu Y, Zhang X, Ye M, Yang J (2018) Developing a long short-term memory (LSTM) based model for predicting water table depth in agricultural areas. J Hydrol 561:918–929CrossRefGoogle Scholar
  43. Zhong W, Yu H, Song L, Zhang X (2011) Combined pretreatment with white-rot fungus and alkali at near room-temperature for improving saccharification of corn stalks. BioResources 6:3440–3451Google Scholar

Copyright information

© Springer Nature B.V. 2019

Authors and Affiliations

  • Mrigank Krishan
    • 1
  • Srinidhi Jha
    • 1
  • Jew Das
    • 1
    Email author
  • Avantika Singh
    • 2
  • Manish Kumar Goyal
    • 1
  • Chandrra Sekar
    • 3
  1. 1.Discipline of Civil EngineeringIndian Institute of Technology IndoreIndoreIndia
  2. 2.School of Computing and Electrical EngineeringIndian Institute of Technology MandiMandiIndia
  3. 3.Department of Civil EngineeringDr. Ambedkar Institute of TechnologyBengaluruIndia

Personalised recommendations