Articles | Volume 12, issue 9
Atmos. Meas. Tech., 12, 5161–5181, 2019
https://doi.org/10.5194/amt-12-5161-2019
Atmos. Meas. Tech., 12, 5161–5181, 2019
https://doi.org/10.5194/amt-12-5161-2019
Research article
26 Sep 2019
Research article | 26 Sep 2019

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

Tongshu Zheng et al.

Related authors

Field evaluation of low-cost particulate matter sensors in high- and low-concentration environments
Tongshu Zheng, Michael H. Bergin, Karoline K. Johnson, Sachchida N. Tripathi, Shilpa Shirodkar, Matthew S. Landis, Ronak Sutaria, and David E. Carlson
Atmos. Meas. Tech., 11, 4823–4846, https://doi.org/10.5194/amt-11-4823-2018,https://doi.org/10.5194/amt-11-4823-2018, 2018
Short summary

Related subject area

Subject: Aerosols | Technique: In Situ Measurement | Topic: Data Processing and Information Retrieval
Quantification of primary and secondary organic aerosol sources by combined factor analysis of extractive electrospray ionisation and aerosol mass spectrometer measurements (EESI-TOF and AMS)
Yandong Tong, Lu Qi, Giulia Stefenelli, Dongyu Simon Wang, Francesco Canonaco, Urs Baltensperger, André Stephan Henry Prévôt, and Jay Gates Slowik
Atmos. Meas. Tech., 15, 7265–7291, https://doi.org/10.5194/amt-15-7265-2022,https://doi.org/10.5194/amt-15-7265-2022, 2022
Short summary
A new method for calculating average visibility from the relationship between extinction coefficient and visibility
Zefeng Zhang, Hengnan Guo, Hanqing Kang, Jing Wang, Junlin An, Xingna Yu, Jingjing Lv, and Bin Zhu
Atmos. Meas. Tech., 15, 7259–7264, https://doi.org/10.5194/amt-15-7259-2022,https://doi.org/10.5194/amt-15-7259-2022, 2022
Short summary
In situ particle sampling relationships to surface and turbulent fluxes using large eddy simulations with Lagrangian particles
Hyungwon John Park, Jeffrey S. Reid, Livia S. Freire, Christopher Jackson, and David H. Richter
Atmos. Meas. Tech., 15, 7171–7194, https://doi.org/10.5194/amt-15-7171-2022,https://doi.org/10.5194/amt-15-7171-2022, 2022
Short summary
The effect of the averaging period for PMF analysis of aerosol mass spectrometer measurements during offline applications
Christina Vasilakopoulou, Iasonas Stavroulas, Nikolaos Mihalopoulos, and Spyros N. Pandis
Atmos. Meas. Tech., 15, 6419–6431, https://doi.org/10.5194/amt-15-6419-2022,https://doi.org/10.5194/amt-15-6419-2022, 2022
Short summary
Calibrating networks of low-cost air quality sensors
Priyanka deSouza, Ralph Kahn, Tehya Stockman, William Obermann, Ben Crawford, An Wang, James Crooks, Jing Li, and Patrick Kinney
Atmos. Meas. Tech., 15, 6309–6328, https://doi.org/10.5194/amt-15-6309-2022,https://doi.org/10.5194/amt-15-6309-2022, 2022
Short summary

Cited articles

Austin, E., Novosselov, I., Seto, E., and Yost, M. G.: Laboratory evaluation of the Shinyei PPD42NS low-cost particulate matter sensor, PLoS One, 10, 1–17, https://doi.org/10.1371/journal.pone.0137789, 2015. 
Breunig, M. M., Kriegel, H. P., Ng, R. T., and Sander, J.: LOF: Identifying Density-Based Local Outliers, available at: http://www.dbs.ifi.lmu.de/Publikationen/Papers/LOF.pdf (last access: 10 December 2018), 2000. 
Byrd, R. H., Lu, P., Nocedal, J., and Zhu, C.: A limited memory algorithm for bound constrained optimization, available at: http://users.iems.northwestern.edu/~nocedal/PDFfiles/limited.pdf (last access: 10 December 2018), 1994. 
CPCB: Air quality monitoring, emission inventory, and source apportionment studies for Delhi, available at: http://cpcb.nic.in/cpcbold/Delhi.pdf, (last access: 10 December 2018), 2009. 
Crilley, L. R., Shaw, M., Pound, R., Kramer, L. J., Price, R., Young, S., Lewis, A. C., and Pope, F. D.: Evaluation of a low-cost optical particle counter (Alphasense OPC-N2) for ambient air monitoring, Atmos. Meas. Tech., 11, 709–720, https://doi.org/10.5194/amt-11-709-2018, 2018. 
Download
Short summary
Here we present 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 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 lifetimes.