Data enrichment toolchain: a use-case for correlation analysis of air quality, traffic, and meteorological metrics in Madrid's smart city

Abstract

In the era of burgeoning data diversity in heterogeneous sources, unlocking valuable insights becomes pivotal. Raw data often lack context and meaning, necessitating the deployment of services that link and enhance data, thereby extracting meaningful patterns and information. For example, exploring the significance of IoT sensors in measuring air quality across cities emphasizes the potential to establish connections between air quality and associated metrics like traffic intensity and meteorological conditions. Introducing the Data Enrichment Toolchain (DET), this study underscores its role in harmonizing and curating diverse datasets. DET operates on linked-data principles and adheres to the NGSI-LD standard, enabling seamless integration and correlation analysis across disparate data domains. The research delves into the intricate relationship between traffic patterns and prevalent air pollutants, utilizing enriched datasets from European cities focusing on the smart city of Madrid as a use-case. Considering the COVID-19 pandemic?s impact on traffic flow and meteorological influences on air quality, the study examines pre-pandemic, pandemic, and post-pandemic traffic scenarios in Madrid. By leveraging DET-enhanced datasets, the investigation aims to unravel nuanced insights into the interplay between traffic, meteorological factors, and air quality, offering valuable implications for urban planning and pollution mitigation strategies.