Air pollution has become a great cause of concern nowadays. The worst affected areas are urban environments especially large metropolitan cities, like Delhi. It has adverse impact on the physical and mental health of human beings. In this context, predicting air pollution has become an urgent need of the hour. This would help people to take safety measures as well as government to enact policies to safeguard the citizens. Traditionally, climatologists and meteorologists have relied on physical simulations for weather forecasting. With the advancement in artificial neural network predicting the future values based on previously observed values has become quite popular. This paper focuses on Time series analysis to predict air pollution in Delhi using LSTM, an artificial recurrent neural network architecture. We use LSTM because it can work on sequences of arbitrary length. We have taken a data-centric approach to predict air pollution and used historical weather data of Delhi that includes several weather variables – atmospheric pressure, temperature, rain, wind direction and wind speed etc.

Air Pollution Prediction, RNN, LSTM, Deep Learning

[1] Y. Zheng, X. Yi, M. Li, R. Li, Z. Shan, E. Chang, and T. Li, “Forecasting fine-grained air quality based on big data,” In the Proceedings of The 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, USA pp. 2267-2276, 2015
[2] Amit Palve, Ajit Patil, Amol Potgantwar “Big Data Analysis Using Distributed Approach on Weather Forecasting Data”, International Journal of Scientific Research in Network Security and Communication , Vol.5, Issue.3, pp. 39-43, 2017.
[3] Gagandeep Kaur, Harmanpreet Kaur “Ensemble based J48 and random forest based C6H6 air pollution detection”, International Journal of Scientific Research in Computer Science and Engineering, Vol.6, Issue.2, pp. 41-50, 2018
[4] D. Mishra, P. Goyal,” Development of artificial intelligence based NO2 forecasting models at Taj Mahal, Agra”, Atmospheric Pollution Research, Vol.6, Issue.1, pp. 99-106, 2015
[5] Kostandina Veljanovska and Angel Dimoski, “Air Quality Index Prediction Using Simple Machine Learning Algorithms”, International Journal of Emerging Trends & Technology in Computer Science, Vol.7, Issue.1, pp. 25-30,2018
[6] Ibrahim Kok, Mehmet Ulvi S¸ and Suat Ozdemir. “A deep learning model for air quality prediction in smart cities”. International Conference on Big Data, USA, pp.1983–1990. IEEE, 2017
[7] S. Hochreiter, J. Schmidhuber “Long Short-Term Memory”, Neural Computation, Vol.9, Issue.8, pp.1735-1780, 1997.
[8] Antonio Gulli, Sujit Pal, “Deep Learning with Keras”, Packt Publishing UK, pp. 187-188, 2017
[9] M. Schuster and K. K. Paliwal, “Bidirectional recurrent neural networks,” IEEE Transactions on Signal Processing, Vol.45, Issue.11, pp.2673–2681, 1997