Sustainable urban mobility: AI and big data identified as game-changers

While the potential is enormous, the authors caution that urban mobility solutions often remain trapped in technocentric approaches that overlook broader sustainability objectives. Policymakers, in many cases, prioritize the deployment of advanced technologies without addressing underlying governance, social, and environmental factors.


CO-EDP, VisionRICO-EDP, VisionRI | Updated: 05-08-2025 21:39 IST | Created: 05-08-2025 21:39 IST
Sustainable urban mobility: AI and big data identified as game-changers
Representative Image. Credit: ChatGPT

A recent study published in Urban Science discusses the transformative potential of Artificial Intelligence (AI) and Big Data in reshaping urban transportation systems. The research underscores how advanced technologies, when effectively governed and inclusively implemented, can drive cities toward more sustainable and efficient mobility solutions.

The study, titled "Leveraging Big Data and AI for Sustainable Urban Mobility Solutions", reviews 72 studies published between 2019 and 2024, supplemented with Norwegian case analyses, to present a comprehensive roadmap for integrating data-driven approaches into urban mobility planning.

How can big data and AI enhance urban mobility systems?

AI and Big Data are redefining how cities manage traffic flows, optimize public transit, and integrate different modes of transportation. Machine learning algorithms support traffic prediction and real-time decision-making, enabling urban planners to anticipate congestion and improve mobility strategies. These technologies allow authorities to create dynamic transport systems that adjust to changing conditions while minimizing environmental impacts.

Digital twin technology emerges as a game-changer in this context. By simulating real-world traffic patterns and scenarios, digital twins offer valuable insights for urban design, infrastructure optimization, and public engagement. This capability helps policymakers test interventions virtually before implementing them, reducing risks and ensuring better outcomes.

The study also highlights that AI and Big Data improve multimodal integration, where different transport options, such as cycling, public transit, and shared vehicles, are combined into seamless user experiences. This integration enhances user satisfaction, reduces reliance on private vehicles, and contributes to lower emissions, aligning with global sustainability targets.

What challenges threaten the implementation of data-driven mobility?

While the potential is enormous, the authors caution that urban mobility solutions often remain trapped in technocentric approaches that overlook broader sustainability objectives. Policymakers, in many cases, prioritize the deployment of advanced technologies without addressing underlying governance, social, and environmental factors.

Key barriers identified include data interoperability issues, where fragmented datasets prevent efficient collaboration between stakeholders. Model validation remains another critical challenge, as inaccurate predictions can undermine trust in AI systems. Moreover, privacy concerns and ethical questions about data collection and usage continue to pose significant hurdles to widespread adoption.

The research stresses that stakeholder engagement is insufficient in many urban planning initiatives. Without the active involvement of communities, private sector players, and policymakers, even the most advanced technologies may fail to deliver meaningful change. The study calls for policies that balance innovation with inclusivity, ensuring that AI and Big Data serve the broader goals of equity and sustainability rather than just efficiency.

Additionally, the study observes a hierarchy of mobility modes, showing that public transit and active transportation methods, such as walking and cycling, outperform private vehicles in terms of sustainability and user satisfaction. However, policies and investments still disproportionately favor private vehicle infrastructure in many regions, contradicting long-term sustainability goals.

What pathways can drive the transition to sustainable urban mobility?

The paper proposes actionable pathways that leverage AI and Big Data to create cities that are not only smarter but also greener and more livable. First, governance frameworks must evolve to incorporate data-informed decision-making, ensuring that technological solutions align with sustainability policies. Governments should promote regulations that encourage interoperability, ethical AI usage, and transparent data practices.

Integrating electrification, automation, and shared mobility models with AI systems can accelerate the transition to low-emission transport. Combining these innovations with intelligent traffic management tools can help reduce congestion, improve air quality, and enhance urban resilience.

Stakeholder collaboration also plays a key role. Public authorities, private technology firms, research institutions, and citizens must work together to co-create solutions that are both technologically sound and socially acceptable. This approach ensures that innovations do not merely serve economic interests but also address environmental and social dimensions.

The study urges policymakers to adopt people-centered mobility policies that prioritize public transit and active transportation while reducing dependence on private vehicles. Investments in cycling lanes, pedestrian infrastructure, and smart public transport systems can enhance sustainability while improving quality of life for urban residents.

Cities that effectively integrate AI and Big Data into their mobility systems stand to gain substantial environmental, economic, and social benefits. However, the absence of robust governance and inclusive policies could result in fragmented solutions that fail to deliver on sustainability promises.

  • FIRST PUBLISHED IN:
  • Devdiscourse
Give Feedback