Investigation of Model Ensemble for Fine-Grained Air Quality Prediction

Air pollution which is detrimental to people's health is a wide spread problem across many countries around the world. Developing better air quality prediction approaches is an important research issue. Existing methods often focus on the prediction of air pollution concentrations, which is not as intuitive to the public as the air quality levels. In this paper, near future fine-grained air quality level prediction task is explored with a series of machine learning ensemble methods. Included ensemble methods are majority voting, averaging, weighted averaging and 16 different stacking tactics. To investigate the performances of these ensemble methods, comprehensive comparative experiments are conducted. Included contrast models are classical Autoregressive Integrated Moving Average (ARIMA), popular deep learning model Long Short-Term Memory (LSTM) neural network, and nine of the base-level models such as Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR) and several boosting models. Datasets acquired from a coastal city Hong Kong and an inland city Beijing are used to train and validate all the models. Experiments show that performances of the ensemble methods outperform most of the individual models, especially when stacking with probability distributions together with engineered original features, which demonstrates the best performance.