Low-cost air quality sensors (LCS) are increasingly used to complement traditional air quality monitoring yet concerns about their accuracy and fitness-for-purpose persist. This scoping review investigates topics, methods, and technologies in the application of LCS networks in recent years that are gaining momentum, focusing on LCS networks (LCSN) operation, drone-based and mobile monitoring, data fusion/assimilation, and community engagement. We identify several key challenges remaining. A major limitation is the absence of unified performance metrics and cross-validation methods to compare different LCSN calibration and imputation techniques and meta-analyses. LCSN still face challenges in effectively sharing and interpreting data due to a lack of common protocols and standardized definitions, which can hinder collaboration and data integration across different systems. In mobile monitoring, LCS siting, orientation, and platform speed are challenges to data consistency of different LCS types and limit the transferability of static calibration models to mobile settings. For drone-based monitoring, rotor downwash, LCS placement, flight pattern, and environmental variability complicate accurate measurements. In integrating LCS data with air quality models or data assimilation, realistic uncertainty quantification, ideally at the individual measurement level, remains a major obstacle. Finally, citizen science initiatives often encounter motivational, technological, economic, societal, and regulatory barriers that hinder their scalability and long-term impact.

Deployment of an air quality low-cost sensor network (AQLCSN), with proper calibration of low-cost sensors (LCS), offers the potential to substantially increase the ability to monitor air pollution. However, to leverage this potential, several drawbacks must be ameliorated, thus the calibration of such sensors is becoming an essential component in their use. Commonly, calibration takes place in a laboratory environment using gasses of known composition to measure the response and a linear calibration is often reached. On site calibration is a promising complementary technique where an LCS and a reference instrument are collocated with the former being calibrated to match the measurements of the latter. In a scenario where an AQLCSN is already operational, both calibration approaches are resource and time demanding procedures to be implemented as frequently repeated actions. Furthermore, sensors are sensitive to the local meteorology and adaptation is a slow process making relocation a complex and expensive option. We concentrate our efforts in keeping the LCS positions fixed and propose to blend a genetic algorithm (GA) with a hybrid stacking (HS) ensemble into the GAHS framework. GAHS employs a combination of batch machine learning algorithms and regularly updated online machine learning calibration function(s) for the whole network when a small number of reference instruments are present. Furthermore, we introduce the concept of spatial online learning to achieve better spatial generalization. The frameworks are tested for the case of Thessaloniki where a total of 33 devices are installed. The AQLCSN is calibrated on the basis of on-site matching with high quality observations from three reference station measurements. The O₃ LCS are successfully calibrated for 8–10 months and the PM₁₀ LCS calibration is evaluated for 13–24 months showing a strong seasonal dependence on their ability to correctly capture the pollution levels.

Air quality (AQ) in urban areas is deteriorating, thus having negative effects on people’s everyday lives. Official air quality monitoring stations provide the most reliable information, but do not always depict air pollution levels at scales reflecting human activities. They also have a high cost and therefore are limited in number. This issue can be addressed by deploying low cost AQ monitoring devices (LCAQMD), though their measurements are of far lower quality. In this paper we study the correlation of air pollution levels reported by such a device and by a reference station for particulate matter, ozone and nitrogen dioxide in Thessaloniki, Greece. On this basis, a corrective factor is modeled via seven machine learning algorithms in order to improve the quality of measurements for the LCAQMD against reference stations, thus leading to its on-field computational improvement. We show that our computational intelligence approach can improve the performance of such a device for PM10 under operational conditions.

Air quality (AQ) modeling is at the forefront of estimating pollution levels in areas where the spatial representativity is low. Large metropolitan areas in Asia such as Beijing face significant pollution issues due to rapid industrialization and urbanization. AQ nowcasting, especially in dense urban centers like Beijing, is crucial for public health and safety. One of the most popular and accurate modeling methodologies relies on black-box models that fail to explain the phenomena in an interpretable way. This study investigates the performance and interpretability of Explainable AI (XAI) applied with the eXtreme Gradient Boosting (XGBoost) algorithm employing the SHapley Additive exPlanations (SHAP) and the Local Interpretable Model-Agnostic Explanations (LIME) for PM_2.5 nowcasting. Using a SHAP-based technique for dimensionality reduction, we identified the features responsible for 95% of the target variance, allowing us to perform an effective feature selection with minimal impact on accuracy. In addition, the findings show that SHAP and LIME supported orthogonal insights: SHAP provided a view of the model performance at a high level, identifying interaction effects that are often overlooked using gain-based metrics such as feature importance; while LIME presented an enhanced overlook by justifying its local explanation, providing low-bias estimates of the environmental data values that affect predictions. Our evaluation set included 12 monitoring stations using temporal split methods with or without lagged-feature engineering approaches. Moreover, the evaluation showed that models retained a substantial degree of predictive power (R² > 0.93) even in a reduced complexity size. The findings provide evidence for deploying interpretable and performant AQ modeling tools where policy interventions cannot solely depend on predictive analytics tools. Overall, the findings demonstrate the large potential of directly incorporating explainability methods during model development for equal and more transparent modeling processes.