Clean air is a basic need for human health and well-being. Forecasting PM2.5 concentrations so that cities can make timely policy responses are of great significance of protecting citizens' respiratory health. This paper proposes a long short-term memory neural network models based on the Sparrow Search Algorithm (SSA-LSTM). The Sparrow Search Algorithm is used to optimize the number of hidden layer nodes, learning rate and number of iterations of the LSTM network to improve the forecasting accuracy of the model. In order to verify the validity of the model, the PM2.5 data onto five large cities including Beijing and Shanghai were used for time series forecasting. Compared with the existing long-short-term memory network model (LSTM), BP neural network models and bilateral long-short-term memory network model (Bilstm), the results show that the forecasting results forecast by this optimization model are the most consistent with the actual PM2.5. The forecasting error is effectively reduced, and the optimization result of the SSA algorithm has a good generalization effect.

No abstract

No abstract

No abstract