Revolutionizing Mobility: Big Data Applications in Transport Planning

Falanga, Antonella; Cartenì, Armando · 2023 · Crossref

DOI: 10.37394/232015.2023.19.129

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 examines the transformative impact of big data on transport planning, focusing on its applications in mobility management and public health analysis. The authors address the challenge of leveraging the "4Vs" of big data (volume, velocity, variety, and value) to improve decision-making in the transportation sector. While big data offers opportunities for real-time monitoring, route optimization, and sustainable planning, it also presents challenges regarding data quality, privacy, and the need for advanced infrastructure and skilled personnel. The study aims to review major big data applications in transportation and analyze two specific Italian case studies: national mobility demand estimation and the correlation between mobility habits and the spread of the COVID-19 pandemic. The research utilizes data from the Italian Ministry of Infrastructure and Transport and the Ministry of Health. The first case study analyzes the "Mobility Trends Observatory," which aggregates data from multimodal operators (including ANAS, Trenitalia, and airport associations) to estimate national demand by transport mode and territory. The second case study employs a multiple linear regression model to link daily certified COVID-19 cases to socio-economic, environmental, healthcare, and mobility variables. This model incorporated data from the "Audimob" monitoring system, which collected mobility habits through interviews before and after the national lockdown, alongside regional data on population density, particulate matter pollution, testing rates, and travel times. The findings from the Mobility Trends Observatory reveal significant fluctuations in mobility demand corresponding with pandemic waves. Car usage on highways dropped radically in early 2020, recovered partially, and declined again during the second wave, with levels returning to pre-pandemic (2019) norms by 2022. High-speed rail demand followed similar trends. The analysis confirms that large-scale, multi-source data is effective for estimating mobility habits only when processed with high professional skills to ensure data quality. Regarding the pandemic study, the regression analysis demonstrated that daily mobility habits significantly influence infection rates. Specifically, the study found that mobility patterns correlate with infections registered three weeks later, suggesting a 21-day period between exposure and detection. This indicates that standard 14-day quarantine periods may underestimate containment needs due to delays in virus detection. Additionally, areas with higher transport accessibility were found to be more rapidly affected by infections. The significance of this work lies in demonstrating the practical utility of big data for both operational transport planning and public health policy. The study highlights that integrating diverse data sources allows for accurate forecasting of mobility needs and infrastructure planning. Furthermore, the identification of a lag between mobility and infection rates provides critical evidence for policymakers, suggesting that mobility restrictions and quarantine protocols must account for delayed epidemiological impacts. The paper concludes that while big data revolutionizes transport efficiency and safety, its successful application depends on robust data governance, interoperability, and specialized analytical expertise.

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.

• exposure measurement