Low-Cost Air Quality Sensor Nodes in a Network Setup: Using Shared Information to Impute Missing Values

Theodosios Kassandros (), Evangelos Bagkis () and Kostas Karatzas ()
Additional contact information
Theodosios Kassandros: Aristotle University of Thessaloniki
Evangelos Bagkis: Aristotle University of Thessaloniki
Kostas Karatzas: Aristotle University of Thessaloniki

A chapter in Advances and New Trends in Environmental Informatics, 2025, pp 35-46 from Springer

Abstract: Abstract Low-Cost Air Quality Sensor Nodes (LCAQSN) are being widely deployed across numerous cities worldwide as a new way for assessing air quality. Despite facing challenges related to accuracy and consistency, these nodes offer valuable insights, substantially reducing the costs associated with monitoring air pollutants. A significant hurdle to address is the occurrence of missing values. In this study, we hypothesize that a network of LCAQSN within the same urban environment can effectively retain and utilize shared information to accurately impute missing values, even in cases with substantial gaps in the time-series data of individual nodes. Employing various Machine Learning techniques, our analysis reveals that a network comprising 26 LCAQSN in the Greater Thessaloniki Area, Greece, with 40.93% missing values, can achieve an imputation accuracy of 0.7 R2 on a simulated test set of 10% of missing values. These findings exhibit great promise and unveil numerous opportunities for leveraging LCAQSN networks further, including data fusion and downscaling applications.

Keywords: Air Quality; Sensors; Imputation; Machine Learning (search for similar items in EconPapers)
Date: 2025
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:prochp:978-3-031-85284-8_3

Ordering information: This item can be ordered from
http://www.springer.com/9783031852848

DOI: 10.1007/978-3-031-85284-8_3

Access Statistics for this chapter

More chapters in Progress in IS from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().