Spatial-Temporal Prediction Method for Air Quality Data Collected by WSN

This study presents a spatial-temporal prediction method for air quality monitoring data. Air quality monitoring sensors were self-made and included multiple types of sensors such as C02, temperature, humidity, and PM2.S. In the spatial prediction phase, we attempt to supplement data at points without observation points by applying distributed compressed sensing. In the temporal prediction phase, we use the LSTM model to predict environmental data. The experiment results show that our method predicts spatial sensor data with high accuracy. Our results suggest that the proposed method is effective in reducing the number of spatial sensors and saving power.