Real-time Air Pollution prediction model based on Spatiotemporal Big data
share
Air pollution is one of the most concerns for urban areas. Many countries have constructed outdoor pollution monitoring stations in major cities to hourly collect air pollutants such as PM2.5, PM10, CO, NO2, SO2 [1]. Recently, there is a research in Daegu city, Korea for real-time air quality monitoring via sensors installed on taxis running across the whole city. The collected data is huge (1-minute interval) and in both Spatial and Temporal format. In this paper, based on this spatiotemporal Big data, we propose a real-time classification Convolutional Neural Network (CNN) model for image-like spatial distribution air pollution. For temporal information in the data, we introduce a combination of a Long-Short Term Memory (LSTM) for time series data and a Neural Network for other pollution influential factors such as weather to build a merged prediction model. This model is simple in architecture but still brings good prediction ability.
READ FULL TEXT