A key challenge associated with low-cost and mobile monitoring systems lies in measurement uncertainty and environmental sensitivity. Sensor responses can be in-fluenced by temperature, humidity, cross-sensitivity to other gases, signal drift, and mechanical vibration during mobile deployment (Lewis & Edwards, 2016; Castell et al., 2017). To address these challenges, recent research has focused on the development of calibration frameworks and data-driven correction methods. Multivariate linear re-gression models, ensemble learning algorithms, neural networks, and other machine learning techniques have been successfully applied to improve the agreement between low-cost sensors and reference-grade instruments (Zimmerman et al., 2018; Malings et al., 2020). These calibration strategies enhance data reliability and enable mobile monitoring systems to function as complementary tools within hybrid monitoring networks. However, most existing studies primarily emphasise environmental compensation and statistical calibration, while fewer investigations explicitly consider dynamic opera-tional factors such as traffic-induced vibration and acceleration effects during vehi-cle-based measurements. This represents a methodological gap in the current body of literature.

A major obstacle for affordable and portable monitoring systems involves uncertainty in measurements and sensitivity to environmental conditions. Various factors can affect how sensors respond, including temperature changes, humidity levels, interference from other gases, signal degradation over time, and physical vibrations that occur when sensors are moved from place to place (Lewis & Edwards, 2016; Castell et al., 2017). Recent studies have worked to tackle these issues by creating calibration systems and correction methods based on data analysis. Researchers have successfully used multivariate linear regression models, ensemble learning algorithms, neural networks, and various other machine learning approaches to make low-cost sensors work more closely with high-quality reference equipment (Zimmerman et al., 2018; Malings et al., 2020). These calibration approaches improve how reliable the data is and allow mobile monitoring systems to work alongside traditional monitoring networks as supporting tools. Most current research, however, focuses mainly on adjusting for environmental factors and statistical calibration. Very few studies have looked closely at dynamic operational issues like vibrations from traffic and acceleration forces that affect measurements taken from vehicles. This creates a research gap in the existing scientific literature.