Abstract
Accurate prediction of PM2.5 concentration can effectively avoid the harm of heavy pollution weather to the human body. The change of PM2.5 concentration results from many factors, and the process is sudden, nonlinear, with evident uncertainty, it is difficult to predict by traditional methods. A PM2.5 prediction model based on long-term and short-term memory neural network was designed by deep learning method to solve this problem. Combined with multiple meteorological, weather, and air pollution index data of PM2.5 in Guangzhou, the long-term and short-term memory network (LSTM) neural network and recurrent neural network (RNN) were used to test the prediction effect. The results show that the LSTM model has a better prediction effect than the RNN model.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have