Geographically Weighted Regression for Air Quality Low-Cost Sensor Calibration

Abstract

This article focuses on the use of Geographically Weighted Regression (GWR) method to correct air quality low-cost sensors measurements. Those sensors are of major interest in the current era of high-resolution air quality monitoring at urban scale, but require calibration using reference analyzers. The results for NO2 are provided along with comments on the estimated GWR model and the spatial content of the estimated coefficients. The study has been carried out using the publicly available SensEURCity dataset in Antwerp, which is especially relevant since it includes 9 reference stations and 34 low-cost sensors collocated and deployed within the city.

Figures (9)

• Figure 1: Map of Antwerp : position sensor and station locations during the deployment phase.
• Figure 2: Weight functions for different values of window $B$
• Figure 3: Timeline of the P2 period colored according to the distribution of days between the samples
• Figure 4: Scatterplot of measured NO$_2$ concentrations at Ref_9 (x-axis) and corrected measurements from sensor ASE_A09 (y-axis), depending on the method (NC, GWR or SGWR). The black line represents the curve $y=x$.
• Figure 5: Boxplot of CV errors for GWR$_5$ and SGWR$_5$ models by sensor. Boxes are colored depending on the location type, as described in Table \ref{['tab:type_loc']}: red (Urban Traffic), orange (Urban Industrial), salmon (Urban Background), blue (Suburban Traffic), light blue (Suburban Background)