Developing a GIS-Based Platform for Real-Time Urban Air Quality Monitoring

Thesis Abstract

Urban air pollution poses a significant public health challenge, particularly in rapidly growing metropolitan areas where inadequate monitoring infrastructure hampers timely response to deteriorating air quality levels. Existing air quality monitoring systems often rely on sparse ground-based sensors with limited spatial coverage, constraining holistic assessment and proactive mitigation efforts. This study aims to develop an integrated Geographic Information System (GIS)-based platform that enables real-time urban air quality monitoring, facilitating enhanced spatial analysis, visualization, and decision-making for urban environmental management. The specific objectives are (1) to design a scalable GIS architecture integrating diverse air quality data sources, (2) to implement a geospatial data collection system utilizing IoT-enabled sensors across strategic urban locations, (3) to develop algorithms for real-time data processing and visualization, and (4) to evaluate the platform’s effectiveness in detecting pollution hotspots and predicting air quality trends. The study adopts a mixed-methods research design combining quantitative data collection and qualitative usability assessment. The population comprises 50 IoT-enabled air quality sensors deployed across a metropolitan district covering approximately 150 square kilometers. A purposive sampling technique is used to select sensor locations based on traffic density, industrial activity, and population density. Data collection instruments include calibrated multi-gas sensors measuring PM2.5, NO2, SO2, and CO levels, and semi-structured interviews with key urban environmental stakeholders. For data analysis, quantitative data from sensors are processed through statistical techniques such as regression analysis and spatial autocorrelation using Moran’s I to identify pollution patterns and hotspots. Geospatial analysis is enhanced via ArcGIS and QGIS platforms, integrating sensor data with auxiliary datasets such as meteorological parameters. Thematic analysis is applied to interview transcripts to assess user needs and system usability. The research adopts the Theory of Planned Behavior to model stakeholder engagement and the just-in-time adaptive intervention framework to enhance real-time decision support. Expected findings include a high correlation between sensor data and existing reference air quality stations, demonstrating the platform’s reliability; identification of spatial and temporal pollution hotspots; and insights into stakeholder preferences and barriers to adopting GIS-based monitoring tools. The platform is anticipated to improve the timeliness and spatial comprehensiveness of air quality data, thereby enabling targeted interventions by city authorities. The integration of IoT sensors with GIS is expected to significantly advance existing urban air quality monitoring models, addressing spatial gaps and detection delays inherent in traditional systems. This study contributes novel methodological insights into deploying scalable geospatial platforms that leverage IoT technology for environmental monitoring, aligning with contemporary smart city paradigms. It enhances theoretical understanding of spatial-temporal analysis of pollution data and stakeholder engagement within environmental management contexts. Practically, the platform provides a replicable framework for urban planners, environmental agencies, and policymakers seeking real-time, spatially explicit air quality information. The research concludes that the GIS-based monitoring system substantially improves pollution surveillance accuracy and responsiveness, recommending broader deployment of integrated geospatial solutions and continuous system refinement based on user feedback. Ultimately, the study underscores the importance of technological innovation in environmental governance, advocating for policy frameworks that support smart, data-driven urban health initiatives. Future research directions include expanding the sensor network coverage, integrating additional data layers such as traffic flows, and exploring machine learning techniques for predictive air quality modeling.