A Long Short-Term Memory Network for Hourly Estimation of [PM.sub.2.5] Concentration in Two Cities of South Korea

• Published in: Applied sciences 2020-06, Vol.10 (11)
• Main Authors: Qadeer, Khaula, Rehman, Wajih Ur, Sheri, Ahmad Muqeem, Park, Inyoung, Kim, Hong Kook, Jeon, Moongu
• Format: Article
• Language: English
• Subjects: Air pollution; Air quality monitoring stations; Distribution; Forecasts and trends; Health aspects; Machine learning; Measurement; Neural networks; Particles; Technology application
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app10113984

Air pollution not only damages the environment but also leads to various illnesses such as respiratory tract and cardiovascular diseases. Nowadays, estimating air pollutants concentration is becoming very important so that people can prepare themselves for the hazardous impact of air pollution beforehand. Various deterministic models have been used to forecast air pollution. In this study, along with various pollutants and meteorological parameters, we also use the concentration of the pollutants predicted by the community multiscale air quality (CMAQ) model which are strongly related to [PM.sub.2.5] concentration. After combining these parameters, we implement various machine learning models to predict the hourly forecast of [PM.sub.2.5] concentration in two big cities of South Korea and compare their results. It has been shown that Long Short Term Memory network outperforms other well-known gradient tree boosting models, recurrent, and convolutional neural networks. Keywords: XGBoost; LightGBM; LSTM; bidirectional LSTM; CNNLSTM; GRU; [PM.sub.2.5]; CMAQ