Aiming at the problems of poor anti-interference ability, low stability and insufficient prediction accuracy of AQI index of traditional air quality monitoring systems, an air quality monitoring system integrating low-power wide-area IoT LPWAN, One-NET cloud platform and recurrent neural network GRU is designed. The system uses LoRa technology to collect environmental parameters, and integrates cloud platform technology and SSA-VMD-GRU model to realize remote monitoring and prediction of AQI index. Through the communication test, the results show that within the communication distance of 1000 meters, the communication rate is above 96%, and the packet loss rate is not more than 4%. The results show that the SSA-VMD-GRU model has a better prediction effect on the AQI index than the traditional GRU model and VMD-GRU model, the RMSE and MAE are reduced, and the prediction error rate is within 3%. The system can realize real-time monitoring of air quality and accurate prediction of AQI index, providing reference for accurate issuance of air quality warnings.