02 May 2023
 | 02 May 2023
Status: this preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).

Development of Low–Cost Air Quality Stations for Next Generation Monitoring Networks: Calibration and Validation of NO2 and O3 Sensors

Alice Cavaliere, Lorenzo Brilli, Bianca Patrizia Andreini, Federico Carotenuto, Beniamino Gioli, Tommaso Giordano, Marco Stefanelli, Carolina Vagnoli, Alessandro Zaldei, and Giovanni Gualtieri

Abstract. A Pre–deployment calibration and a field validation of two low-cost (LC) stations equipped with O3 and NO2 metal oxide sensors were addressed. Pre–deployment calibration was performed after developing and implementing a comprehensive calibration framework including several supervised learning models, such as univariate linear and non–linear algorithms, as well as multiple linear and non–linear algorithms. Univariate linear models included linear and robust regression, while univariate non–linear models included support vector machine, random forest, and gradient boosting. Multiple models consisted of both parametric and non-parametric algorithms. Internal temperature, relative humidity and gaseous interference compounds proved to be the most suitable predictors for multiple models, as they helped effectively mitigate the impact of environmental conditions and pollutant cross-sensitivity on sensor accuracy. A feature analysis, implementing Dominance analysis, feature permutations and, SHapley Additive exPlanations method, was also performed to provide further insight into the role played by each individual predictor and its impact on sensor performances. This study demonstrated that while multiple random forest (MRF) returned higher accuracy than multiple linear regression (MLR), it did not accurately represent physical models beyond the Pre–deployment calibration dataset, so that a linear approach may overall be a more suitable solution. Furthermore, as well as being less computationally demanding and generally more suitable for non-experts, parametric models such as MLR have a defined equation that also includes a few parameters, which allows easy adjustments for possible changes over time. Thus, drift correction or periodic automatable recalibration operations can be easily scheduled, which is particularly relevant for NO2 and O3 metal oxide sensors: as demonstrated in this study, they performed well with the same linear model form, but required unique parameter values due to inter-sensor variability.

Alice Cavaliere et al.

Status: open (until 07 Jul 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Alice Cavaliere et al.

Data sets

Dataset Alice Cavaliere

Model code and software

Jupyter notebook Alice Cavaliere

Alice Cavaliere et al.


Total article views: 172 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
115 52 5 172 8 3 4
  • HTML: 115
  • PDF: 52
  • XML: 5
  • Total: 172
  • Supplement: 8
  • BibTeX: 3
  • EndNote: 4
Views and downloads (calculated since 02 May 2023)
Cumulative views and downloads (calculated since 02 May 2023)

Viewed (geographical distribution)

Total article views: 213 (including HTML, PDF, and XML) Thereof 213 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 04 Jun 2023
Short summary
This paper assessed calibration models for two LC stations equipped with O3 and NO2 MOS sensors. Environmental parameters were found to improve accuracy in both linear and black box models. Moreover interpretability methods as SHapley Additive exPlanations helped identify physical patterns and potential problems of these models in field validation. Results showed both sensors performed well with the same linear model form, but unique coefficients were required for inter–sensor variability.