Deep Learning for Air Quality Forecasts: a Review
- PDF / 641,761 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 15 Downloads / 214 Views
AIR POLLUTION (H ZHANG AND Y SUN, SECTION EDITORS)
Deep Learning for Air Quality Forecasts: a Review Qi Liao 1,2 & Mingming Zhu 1,2 & Lin Wu 1
&
Xiaole Pan 1 & Xiao Tang 1 & Zifa Wang 1,2,3
# Springer Nature Switzerland AG 2020
Abstract Air pollution is one of major environmental issues in the twenty-first century due to global industrialization and urbanization. Its mitigation necessitates accurate air quality forecasts. However, current state-of-the-art air quality forecasts are limited from highly uncertain chemistry-transport models (CTMs), shallow statistical methods, and heterogeneous and incomplete observing networks. Recently, deep learning has emerged as a general-purpose technology to extract complex knowledge using massive amount of data and very large networks of neurons and thus has the potential to break the limits of air quality forecasts. Here, we provide a brief review of recent attempts on using deep learning techniques in air quality forecasts. We first introduce architectures of deep networks (e.g., convolutional neural networks, recurrent neural networks, long short-term memory neural networks, and spatiotemporal deep network) and their relevance to explore the nonlinear spatiotemporal features across multiple scales of air pollution. We then examine the potential of deep learning techniques for air quality forecasts in diverse aspects, namely, data gap filling, prediction algorithms, improvements of CTMs, estimations with satellite data, and source estimations for atmospheric dispersion forecasts. Finally, we point out some prospects and challenges for future attempts on improving air quality forecasts using deep learning techniques. Keywords Air quality forecasts . Deep learning . Neural network
Introduction Air pollution is a widespread environmental issue in the twentyfirst century. Particularly in densely populated megacities, air pollution has been regarded as one of the largest environmental threads [1]. The primary contributors to air pollution are humaninduced activities such as industrial productions, moving vehicle This article is part of the Topical Collection on Air Pollution * Lin Wu [email protected] * Xiaole Pan [email protected] 1
State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, China
2
College of Earth Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
3
Center for Excellence in Urban Atmospheric Environment, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen 361021, China
exhausts, and coal combustion. These human activities produce gaseous pollutants and particulate matter into the atmosphere, which cause acute and chronic effects on human health, especially for young and elderly [2]. The World Health Organization (WHO) estimated that air pollution has caused around seven million premature deaths across the world in 2012, of which atmospheric aerosol plays a significant contribution [3]. Among those
Data Loading...
