Srinivasa Rao Kurapati et al, IJSRR 2019, 8(2), 4576-4585 IJSRR, 8(2) April. – June., 2019 Page 4576 Research article Available online www.ijsrr.org ISSN: 2279–0543 I nternational Journal of Scientific Research and Reviews Bidirectional Long Short Term Memory based Recurrent Neural Networks for Air Quality Prediction: Case of Visakhapatnam Srinivasa Rao Kurapati 1* , Lavanya Devi G 2 and Ramesh Neelapu 3 1* Research Scholar, Department of Computer Science and System Engineering, Andhra University College of Engineering; sri.kurapati@gmail.com 2 Assistant Professor, Department of Computer Science and System Engineering, Andhra University College of Engineering; lavanyadevig@yahoo.co.in 3 Research Scholar, Department of Computer Science and System Engineering, Andhra University College of Engineering; rameshauvsp@gmail.com ABSTRACT Accurate forecasting of the air quality has become a challenging task in today's scenario. There is an increasing concern on air quality ambience studies to identify and extract patterns for estimating and predicting pollutants' concentrations for a specific geographical area. With the current advances in computation, innovative modeling approaches for effective prediction of air quality have been initiated. The proposed study puts forward Bidirectional Long Short Term Memory (BI-LSTM) which considers both forward and backward dependencies to predict air quality of the city Visakhapatnam.BI-LSTM model is accurate in predicting concentration levels of pollutants by extracting temporal patterns in the past data of the pollutants. Experimental results show that proposed BI-LSTM model achieves higher prediction accuracy when compared with baseline models. Furthermore, this model may be enriched by convolutional recurrent neural networks. KEYWORDS: air quality; air pollutants’ concentrations, prediction, bidirectional long short term memory (BI-LSTM), temporal patterns, convolutional recurrent neural networks *Corresponding author Srinivasa Rao Kurapati Research Scholar, Department of Computer Science and System Engineering, Andhra University College of Engineering, Visakhapatnam - 530003, A.P, INDIA. Email: sri.kurapati@gmail.com