Machine learning techniques to improve the field performance of low-cost air quality sensors

Tony Bush, Nick Papaioannou, Felix Leach*, Francis D. Pope, Ajit Singh, G. Neil Thomas, Brian Stacey, Suzanne Bartington

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

35 Downloads (Pure)

Abstract

Low-cost air quality sensors offer significant potential for enhancing urban air quality networks by providing higher-spatiotemporal-resolution data needed, for example, for evaluation of air quality interventions. However, these sensors present methodological and deployment challenges which have historically limited operational ability. These include variability in performance characteristics and sensitivity to environmental conditions. In this work, we investigate field "baselining"and interference correction using random forest regression methods for low-cost sensing of NO2, PM10 (particulate matter) and PM2.5. Model performance is explored using data obtained over a 7-month period by real-world field sensor deployment alongside reference method instrumentation. Workflows and processes developed are shown to be effective in normalising variable sensor baseline offsets and reducing uncertainty in sensor response arising from environmental interferences. We demonstrate improvements of between 37g % and 94g % in the mean absolute error term of fully corrected sensor datasets; this is equivalent to performance within ±2.6g ppb of the reference method for NO2, ±4.4g μgg m-3 for PM10 and ±2.7g μgg m-3 for PM2.5. Expanded-uncertainty estimates for PM10 and PM2.5 correction models are shown to meet performance criteria recommended by European air quality legislation, whilst that of the NO2 correction model was found to be narrowly (g1/45g %) outside of its acceptance envelope. Expanded-uncertainty estimates for corrected sensor datasets not used in model training were 29g %, 21g % and 27g % for NO2, PM10 and PM2.5 respectively.

Original languageEnglish
Pages (from-to)3261-3278
Number of pages18
JournalAtmospheric Measurement Techniques
Volume15
Issue number10
DOIs
Publication statusPublished - 1 Jun 2022

Bibliographical note

Funding Information:
Financial support. This research was funded by the Natural Environment Research Council (grant no. NE/V010360/1). Its forerunning pilot project was funded by the National Institute for Health and Care Research (NIHR130095; NIHR Public Health Research). The views expressed are those of the author(s) and not necessarily those of the NIHR or the Department of Health and Social Care. This publication arises in part from research funded by Research England’s Strategic Priorities Fund (SPF) quality related (QR) allocation.

ASJC Scopus subject areas

  • Atmospheric Science

Fingerprint

Dive into the research topics of 'Machine learning techniques to improve the field performance of low-cost air quality sensors'. Together they form a unique fingerprint.

Cite this