A U-net Architecture Based Model for Precise Air Pollution Concentration Monitoring

Feihong Wang, Gang Zhou (), Yaning Wang, Huiling Duan, Qing Xu, Guoxing Wang and Wenjun Yin
Additional contact information
Feihong Wang: Insights Value Technology
Gang Zhou: Insights Value Technology
Yaning Wang: Insights Value Technology
Huiling Duan: Insights Value Technology
Qing Xu: Insights Value Technology
Guoxing Wang: Insights Value Technology
Wenjun Yin: Insights Value Technology

A chapter in AI and Analytics for Smart Cities and Service Systems, 2021, pp 65-75 from Springer

Abstract: Abstract Convolutional Neural Network (CNN) is one of the main deep learning algorithms that has gained increasing popularity in a variety of domains across the globe. In this paper, we use U-net, one of the CNN architectures, to predict spatial PM2.5 concentrations for each 500 m × 500 m grid in Beijing. Different aspects of data including satellite data, meteorological data, high density PM2.5 monitoring data and topography data were taken into consideration. The temporal and spatial distribution patterns of PM2.5 concentrations can be learned from the result. Then, a customized threshold was added for each predicted grid PM2.5 concentration to define high-value areas to find precise location of potential PM2.5 discharge events.

Keywords: Convolutional Neural Network (CNN); U-net; Deep learning; PM2.5 concentration (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-3-030-90275-9_6

Ordering information: This item can be ordered from
http://www.springer.com/9783030902759

DOI: 10.1007/978-3-030-90275-9_6

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().