System for Detecting and Forecasting PM2.5 Concentration Levels Using Long Short-Term Memory and LoRa

摘要: Atmospheric particulate matter, such as PM2.5, contributes to air pollution negatively affecting human health. Many factors determine the change of PM2.5 concentration levels, which can be very sudden, nonlinear, and uncertain. Hence, traditional methods are not always suitable for predicting exact amount in air. Effective forecasting levels tell people condition support country's sustainable development; hence, values has an important social long-term economic significance. This study proposes a system monitoring other pollutants using long-range wireless data communication technology LoRa cloud-based model, includes proprietary terminal device. LoRa's excellent characteristics, low-power consumption long range, allow effectively obtaining history readings. A prediction model based on short-term memory (LSTM) cyclic neural network is utilized predict next few hours' carry out quality index analysis PM2.5. Experiments atmospheric pollutant datasets collected specifically this from North China University Technology 2019 show that analyze well accurately hourly variation trend