Journal cover Journal topic
Atmospheric Measurement Techniques An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 3.248 IF 3.248
  • IF 5-year value: 3.650 IF 5-year
    3.650
  • CiteScore value: 3.37 CiteScore
    3.37
  • SNIP value: 1.253 SNIP 1.253
  • SJR value: 1.869 SJR 1.869
  • IPP value: 3.29 IPP 3.29
  • h5-index value: 47 h5-index 47
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 60 Scimago H
    index 60
Discussion papers
https://doi.org/10.5194/amt-2019-55
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-2019-55
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research article 01 Mar 2019

Research article | 01 Mar 2019

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Atmospheric Measurement Techniques (AMT).

Gaussian Process regression model for dynamically calibrating a wireless low-cost particulate matter sensor network in Delhi

Tongshu Zheng1, Michael H. Bergin1, Ronak Sutaria2, Sachchida N. Tripathi3, Robert Caldow4, and David E. Carlson1,5 Tongshu Zheng et al.
  • 1Department of Civil and Environmental Engineering, Duke University, Durham, NC 27708, USA
  • 2Respirer Living Sciences Pvt. Ltd, 7, Maheshwar Nivas, Tilak Road, Santacruz (W), Mumbai 400054, India
  • 3Department of Civil Engineering, Indian Institute of Technology Kanpur, Kanpur, Uttar Pradesh 208016, India
  • 4TSI Inc., 500 Cardigan Road, Shoreview, MN 55126, USA
  • 5Department of Biostatistics and Bioinformatics, Duke University, Durham, NC 27708, USA

Abstract. Wireless low-cost particulate matter sensor networks (WLPMSNs) are transforming air quality monitoring by providing PM information at finer spatial and temporal resolutions; however, large-scale WLPMSN calibration and maintenance remain a challenge because the manual labor involved in initial calibration by collocation and routine recalibration is intensive, the transferability of the calibration models determined from initial collocation to new deployment sites is questionable as calibration factors typically vary with urban heterogeneity of operating conditions and aerosol optical properties, and the stability of low-cost sensors can develop drift or degrade over time. This study presents a simultaneous Gaussian Process regression (GPR) and simple linear regression pipeline to calibrate and monitor dense WLPMSNs on the fly by leveraging all available reference monitors across an area without resorting to pre-deployment collocation calibration. We evaluated our method for Delhi where the PM2.5 measurements of all 22 regulatory reference and 10 low-cost nodes were available in 59 valid days from 1 January 2018 to 31 March 2018 (PM2.5 averaged 138 ± 31 μg m−3 among 22 reference stations) using a leave-one-out cross-validation (CV) over the 22 reference nodes. We showed that our approach can achieve an overall 30 % prediction error (RMSE: 33 μg m−3) at a 24 h scale and is robust as underscored by the small variability in the GPR model parameters and in the model-produced calibration factors for the low-cost nodes among the 22-fold CV. We revealed that the accuracy of our calibrations depends on the degree of homogeneity of PM concentrations, and decreases with increasing local source contributions. As by-products of dynamic calibration, our algorithm can be adapted for automated large-scale WLPMSN monitoring as simulations proved its capability of differentiating malfunctioning or singular low-cost nodes within a network via model-generated calibration factors with the aberrant nodes having slopes close to 0 and intercepts close to the global mean of true PM2.5 and of tracking the drift of low-cost nodes accurately within 4 % error for all the simulation scenarios. The simulation results showed that ~20 reference stations are optimum for our solution in Delhi and confirmed that low-cost nodes can extend the spatial precision of a network by decreasing the extent of pure interpolation among only reference stations. Our solution has substantial implications in reducing the amount of manual labor for the calibration and surveillance of extensive WLPMSNs, improving the spatial comprehensiveness of PM evaluation, and enhancing the accuracy of WLPMSNs.

Tongshu Zheng et al.
Interactive discussion
Status: open (until 03 May 2019)
Status: open (until 03 May 2019)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Tongshu Zheng et al.
Tongshu Zheng et al.
Viewed  
Total article views: 418 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
321 94 3 418 19 1 3
  • HTML: 321
  • PDF: 94
  • XML: 3
  • Total: 418
  • Supplement: 19
  • BibTeX: 1
  • EndNote: 3
Views and downloads (calculated since 01 Mar 2019)
Cumulative views and downloads (calculated since 01 Mar 2019)
Viewed (geographical distribution)  
Total article views: 209 (including HTML, PDF, and XML) Thereof 205 with geography defined and 4 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
Latest update: 23 Mar 2019
Publications Copernicus
Download
Short summary
This study presents a simultaneous Gaussian Process regression (GPR) and linear regression pipeline to calibrate and monitor dense wireless low-cost particulate matter sensor networks (WLPMSNs) on-the-fly by using all available reference monitors across an area. Our robust approach can achieve an overall 30 % prediction error at a 24 h scale, can differentiate malfunctioning nodes, and track drift. Our solution can substantially reduce manual labor for managing WLPMSNs and prolong their lifetime.
This study presents a simultaneous Gaussian Process regression (GPR) and linear regression...
Citation