Air pollution forecasting using rnn with lstm
Air pollution is increasingly serious with industrial development. In particular the PM (Particulate Matter) has been shown that it has a great correlation with human health that concluded short exposures to PM10 and PM2.5 are associated with increases in mortality. Therefore, to effectively monitor and forecast PM2.5 concentration is an important issue. This project is an approach to forecast PM2.5 concentration using RNN (Recurrent Neural Network) with LSTM (Long Short-Term Memory). exploit Keras, which is a high-level neural networks API written in Python and capable of running on top of TensorFlow, to build a neural network and run RNN with LSTM through TensorFlow. The training dataset used that reports on the weather and the level of pollution each hour for five years at the US embassy in Beijing, China.