Development of low-cost air quality stations for next-generation monitoring networks: calibration and validation of NO2 and O3 sensors

A pre-deployment calibration and a field validation of two low-cost (LC) stations equipped with O3 and NO(2 )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, and multiple linear and non-linear algorithms. Univariate linear models included linear and robust regression, while univariate non-linear models included a 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 the 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 a higher accuracy than multiple linear regression (MLR), it did not accurately represent physical models beyond the pre-deployment calibration dataset, so 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 intersensor variability.