Hybrid Time-Series Framework for Daily-Based PM<sub>2.5</sub> Forecasting
Pei-Wen Chiang, Shi‐Jinn Horng
Abstract
The impact of fine particulate matter on health has captured attention worldwide. Many studies have proven that fine particulate matter harms the respiratory system and the cardiovascular system. To prevent people from being harmed, many scientific research studies on PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> prediction have been conducted in recent years. Accurate PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> forecasting can not only alert people to stay away from concentrated areas but also provide the government with environmental policies in the future. In this paper, we propose a hybrid time-series prediction framework for daily-based PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> forecasting. The proposed framework consists of three components: the autoencoder, the dilated convolutional neural network, and the gated recurrent unit. The experimental dataset with 76 monitoring stations from the Taiwan Environmental Protection Administration is applied for comparison of the baseline and the proposed models. The proposed model is not only for the specified city-/county-wide region but also for the particular monitoring station/site to predict PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> concentration. By considering air quality data, meteorological data, and geographical data simultaneously, the proposed model can increase the accuracy of PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> prediction. In addition, the proposed PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> forecasting model can learn the location-centric spatial features and the daily-based temporal features simultaneously. The experimental results show that the prediction accuracy of the proposed model is superior to those of the baseline models.