• PDF / 1,644,130 Bytes
• 18 Pages / 595.224 x 790.955 pts Page_size
• 26 Downloads / 237 Views

DOWNLOAD

REPORT

---

RESEARCH ARTICLE

Combining forward with recurrent neural networks for hourly air quality prediction in Northwest of China Zhili Zhao1 · Jian Qin1 · Zhaoshuang He1 · Huan Li1 · Yi Yang1 · Ruisheng Zhang1 Received: 25 October 2019 / Accepted: 17 April 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020

Abstract Data-driven statistical air quality prediction methods usually build models fast with moderate accuracy and have been studied a lot in recent years. However, due to the complexity of air quality prediction which usually involves multiple factors, such as meteorological, spatial, and temporal properties, it is still a challenge to propose a model with required accuracy. In this paper, we propose a hybrid ensemble model CERL to exploit the merits of both forward neural networks and recurrent neural networks that are designed for handling time serial data to predict air quality hourly. Measured air pollutant factors including Air Quality Index (AQI), PM2.5 , PM10 , CO, SO2 , NO2 , and O3 are used as input to predict air quality from 1 to 8 h ahead. Based on the air quality prediction evaluation in Lanzhou and Xi’an, which are two important provincial capitals in Northwest China, CERL provides better performance over other baseline models. Moreover, as the step length increases, CERL has more obvious improvement. For example, the improvements of CERL in the 1-step, 3-step, 5-step, and 8-step prediction for PM2.5 in Lanzhou are 1.82%, 8.01%, 9.98%, and 20.03%, respectively. The superiority of CERL is also proved by a hypothesis Diebold Mariano test with level of significance 5%. Keywords Air quality · Machine learning · Serial data · SSA · Sliding window · Neural network

Introduction Due to rapid population growth and backward economic levels, air pollution has been one of the major problems perplexing many developing countries. According to the latest world air quality report released by AirVisual (2019), Asian locations dominate the highest 100 average PM2.5 levels during 2018, with cities in India, China, Pakistan, and Bangladesh occupying the top 50 cities (AirVisual 2018). China is the largest developing country in the world, and many cities of China have suffered from serious air pollution in the past few years, such as Hotan, Shijiazhuang, Baoding, Xianyang, Jiaozuo, and Cangzhou. Although China’s air pollution exposures have stabilized and even begun to decline slightly after several years of strict restrictions on industrial emissions and the use

Responsible Editor: Constantini Samara  Zhili Zhao

[email protected] 1

School of Information Science and Engineering, Lanzhou University, Lanzhou, 730000, China

of fossil fuels for indoor heating and cooking (HEI and IHME 2018), efforts are still needed to protect environment at a high level. Sulfur oxides, carbon oxides, nitrogen oxides, hydrocarbons, particulate matter 10 (PM10 ), and particulate matter 2.5 (PM2.5 ) in the atmosphere are the main contributors to air pollution, and many efforts have been put into predicting air quality base