Application of Deep Learning Technique for prediction of AQI

The rapid increase in urbanization and industrialization, with increasing population, is the reason behind the increase in air pollution. Keeping in mind the population's health prediction of Air Quality Index (AQI) is necessary. AQI is a parameter that tells about the quality of air and helps the public in taking the required measures accordingly. In India as per the Central Pollution Control Board (CPCB), AQI ranges from 0 to 500 where 0-50 represents the good AQI and 401-500 is the severe AQI. In this paper, AQI prediction is done using long short term memory(LSTM), bidirectionalLSTM (BiLSTM), StackedLSTM and gated recurrent unit(GRU). The incapability of handling long term dependency with recurrent neural network(RNN) brought LSTM into the picture. LSTM handles the problem of vanishing gradient effectively. The stackedLSTM stands out from other models with the highest R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> value and lowest mean square error(MSE).