Big Data Analytics and Visualization in Traffic Monitoring

Bachechi, Chiara; Po, Laura; Rollo, Federica · 2021 · OpenAlex-citations

DOI: 10.1016/j.bdr.2021.100292

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper presents the Trafair Traffic Dashboard (TTD), a visual analytics system designed to monitor urban traffic and assess its impact on air quality. The research addresses the challenge of transforming large volumes of spatio-temporal traffic data into actionable insights for public authorities and citizens. Motivated by the significant contribution of road transport to urban air pollution, specifically nitrogen dioxide levels, the study aims to provide tools for identifying traffic trends, detecting congestion, and understanding how vehicle fleet changes affect environmental quality. The system is part of the broader Trafair project, which seeks to support sustainable mobility decisions in smart cities. The methodology involves a comprehensive data framework that ingests, cleans, models, and visualizes traffic data. The architecture utilizes a PostgreSQL database enhanced with PostGIS for geospatial handling and TimescaleDB for efficient time-series management. Data sources include real-time sensor measurements (flow and speed) and OpenStreetMap road network data. The pipeline employs a two-step cleaning process: a speed-flow correlation filter and an anomaly detection algorithm based on Seasonal-Trend Decomposition using Loess (STL) and Interquartile Range analysis. Cleaned data feed into a traffic simulation model to estimate flows across the entire road network, which subsequently serves as input for an air pollutant dispersion model. These computationally intensive processes are executed on a High Performance Computing platform. The resulting data are exposed via GeoServer and visualized through an Angular-based interactive dashboard. The study demonstrates the framework’s applicability through case studies in Modena, Italy, and Santiago de Compostela, Spain. The dashboard enables users to explore real-time and historical traffic data, visualize sensor reliability, and analyze average weekly trends. Key findings highlight the system's ability to detect behavioral similarities between sensors, identify unusual events, and simulate traffic flow under hypothetical vehicle fleet scenarios. The integration of traffic simulation with air quality modeling allows for the visualization of how specific traffic patterns contribute to pollution levels, addressing a gap in existing dashboards that often treat traffic and environmental data separately. The significance of this work lies in providing a scalable, open-source solution for urban traffic and air quality monitoring. By combining real-time sensor data with simulation models, the TTD offers a unified interface for analyzing the spatio-temporal evolution of traffic and its environmental consequences. The authors conclude that such visual analytics tools empower decision-makers to identify congested areas, understand seasonal traffic behaviors, and evaluate mitigation strategies for reducing traffic-related pollution. The framework’s design ensures adaptability to different cities and data sources, supporting the broader goals of sustainable urban development and improved air quality management.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• traffic density

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Methodological Resource: dataset resource