Geographically Weighted Regression for Air Quality Low-Cost Sensor Calibration

2025-10-07

AI Summary

To address insufficient calibration accuracy of low-cost air quality sensors in high-resolution urban monitoring, this paper proposes a localized calibration method based on Geographically Weighted Regression (GWR). Unlike conventional global regression models, GWR explicitly accounts for spatial heterogeneity in calibration parameters, thereby enhancing the modeling capability for non-stationary spatial relationships. Empirical evaluation is conducted using NO₂ measurements from nine reference stations and 34 low-cost microsensors in Antwerp, Belgium, drawn from the SensEURCity dataset. Results demonstrate that GWR significantly reduces calibration error compared to global approaches; moreover, its spatially varying coefficients exhibit clear geographic patterns with strong physical interpretability. This work establishes a novel paradigm for fine-grained, physically interpretable calibration of urban sensor networks, advancing both methodological rigor and practical applicability in hyperlocal air quality monitoring.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Local Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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 micro-sensors collocated and deployed within the city.

Problem

• Calibrating low-cost air quality sensors using geographically weighted regression
• Correcting NO2 measurements from urban micro-sensors with spatial calibration
• Improving sensor accuracy using reference stations and spatial coefficient modeling

Innovation

• Geographically Weighted Regression for sensor calibration
• Corrects measurements using spatial coefficient variations
• Leverages dense network of reference stations