IEEE BigData

2026 IEEE International Conference on Big Data

Call for Special Session on Neo Urban Metabolism

Special Session on Neo Urban Metabolism in IEEE BigData 2026

Harnessing Big Data for Sustainable and Human-Centered Cities

This IEEE BigData 2026 Special Session explores "Neo Urban Metabolism," a new paradigm leveraging big data and AI to understand, design, and evolve sustainable and human-centric cities.

Overview

Neo urban metabolism extends the concept of "urban metabolism"—the organic growth and evolution of cities—into the digital age. It recognizes cities as complex systems where diverse flows (people, goods, energy, information, experiences) interact, shaping our living environment. By analyzing these flows through big data, we gain insights into urban dynamics, enabling more informed decision-making for sustainable development.

For the deployment of the neo urban metabolism concept, Data spaces are dispensable because they allow the integration of heterogeneous urban datasets across organizations while respecting governance, qualification and privacy concerns. This connected ecosystem enables us to analyze complex urban interactions using sensitive and confidential data, leading to new approaches in generative urban design. Simulations and digital twins can be used to explore different scenarios and design solutions that optimize efficiency, sustainability, and human well-being.

Neo urban metabolism goes beyond mere optimization. It recognizes the importance of intangible factors like happiness, well-being, social connections, and everyday experiences in shaping vibrant urban environments.

The session emphasizes analyzing hidden opportunities for creativity and well-being, as well as identifying latent problems often overlooked by conventional metrics. Factors like emotions, curiosity, narratives, and daily rhythms influence how people experience cities. Digital technologies can help us uncover these patterns and design more human-centric spaces.

Details of the scope of this special session

Areas and places for human life can be viewed as systems where diverse flows circulate and interact — including flows of people, goods, energy, information, and experiences. These collectively shape a new power source of urban metabolism.Urban metabolism, an extension of metabolism originally proposed in the middle of the 20th century by architects, means organic growth and evolution of cities, and places to be cities in the future, to create a sustainable human life environment and systems of systems supporting this environment. We are already finding Neo urban metabolism,a new phase of urban metabolism involving big data and information technologies, including artificial intelligence.

Recent advances in mobility sensing technologies and urban data infrastructures have enabled the observation of human activities in real spaces at unprecedented spatial and temporal scales. Mobility data reveal how people move, interact, and form communities in everyday urban life. However, mobility data alone are not sufficient for understanding urban dynamics, which involve unexpected events. Neo urban metabolism is our vision to make a trend toward a sustainable, reliable, and evolving human-life environment, by making a network of existing and emerging data which may be potentially relevant to urban environments and societal activities of humans. Such data may be on:

  • transportation and logistics flows
  • environmental conditions and climate data
  • economic and commercial activities
  • urban infrastructure and spatial configurations
  • social interactions and human well-being
  • energy consumption and carbon emissions

Data spaces enable such heterogeneous datasets to be connected across organizations while respecting governance, privacy, and ownership of data providers. By integrating urban data through data spaces, it becomes possible for humans or artificial intelligence to analyze the complex interactions among urban flows and to explore new approaches to generative urban design, where human activities and their environment can be simulated, designed, and evolved to support sustainable and human-centered environments.

An important perspective in this context is that places of human life are not only systems of efficiency or optimization. Urban environments nurture human experiences that are often subtle and difficult to quantify — such as casual encounters, slow walks, just talking for talking, small discoveries in neighborhoods, or shared moments of everyday happiness. These small sources of well-being hidden in the corners of cities may play a significant role in human well-being and social vitality. At the same time, places may contain latent problems that remain unnoticed when urban systems are evaluated only through conventional metrics such as efficiency or productivity. Understanding and realizing neo urban metabolism, therefore, requires attention to both:

  • hidden opportunities for human well-being and creativity, and
  • latent problems embedded in urban environments.

Thus, human psychological factors — including emotions, curiosity, narratives, and rhythms of daily life — influence how people experience and shape places for human life. Digital technologies such as big data analytics, AI, and chance discoveries can help discover these patterns and support new approaches for designing and evolving urban environments. Finally, we should recognize that, in this era of radical development of AI, we humans are still responsible for sustaining the earth as a place for our own lives. All evidence, findings, and motions that are obtained or generated from data should be managed finally not only by data scientists but also by experts of urban design and other domains contributing to the living environment of humans. Thus, the process to create, use, reuse, connect, and share knowledge, together with education, should be positioned as an essence of neo urban metabolism.

This special session, therefore, invites contributions exploring how mobility data and other urban data can be integrated in data spaces to analyze urban metabolism, support generative urban design, and foster urban vitality and human life evolution, including studies on human factors and education, in order to go ahead to neo urban metabolism.

Relevant Areas

Topics include, but are not limited to:

  • Analysis
    • Human Activities and Urban Metabolism
    • Analysis of mobility patterns and human activities in urban spaces;
    • Modeling flows of people, goods, energy, and information;
    • Understanding interactions among mobility, infrastructure, and economic activities;
    • Analysis of collective behavior and social interactions;
    • Modeling epidemics, risks, and urban resilience.
    • Chance discoveries from in and behind markets
  • Synthesis
    • Generative Urban Design by humans and AI
    • Generative approaches for designing urban environments using urban data;
    • Data-driven urban planning and placemaking;
    • Simulation and urban digital twin approaches;
    • Design strategies for walkability, liveliness, and human well-being;
    • Participatory urban design supported by big data and AI;
    • Education and knowledge utility for urban design experts
  • Distribution and Sharing (Data Spaces)
    • Global dataspace platforms;
    • Data platform federation technology such as connector and broker technology, data collection technology, and trust federation;
    • Data processing platform such as DWH (Data Warehouse) , Data Lake, Data Weaves, and Data Mesh.
    • Secure data sharing/processing platform such as data platform with privacy enhancing technologies (PETs), federated learning (FL), blockchain, trusted web, and decentralized identifiers (DiDs);
    • Data qualification such as data trust, data quality and data traceability;
    • Data governance rules, law, and policy including data sovereignty and DFFT;
    • Technologies for AI-ready dataspaces such as MCP (Model Context Protocol), RAG (Retrieval Augmented Generation), F-RAG (Federated RAG), Agentic RAG and AI Agent.
  • Data Sciences
    • Machine learning and generative AI for urban systems;
    • Predictive and generative modeling of urban dynamics;
    • Data visualization and interactive analytics for urban systems design;
    • Trust, privacy, and governance in urban data ecosystems;
    • Chance discovery (identifying risks and opportunities in dynamic environments).
  • Human Life with Neo Urban Metabolism
    • Understanding happiness in daily experiences in living environment;
    • Human narratives and subjective experiences in urban environments;
    • Slow rhythms and everyday life in urban spaces;
    • Comforts and ethics in urban life with AI and data space;
    • Overlooked opportunities and latent problems in real space of human life.

Important Dates

  • Paper submission: October 12, 2026 (strict)
  • Notification of acceptance: November 3, 2026
  • Camera-ready paper due: November 13, 2026 (strict)
  • Paper submission: PDF in a 2-column IEEE format.
  • Accepted papers will be published in the conference proceedings of IEEE BigData.
  • All accepted papers must be presented by one of the authors.

Chairs

  • Noboru Koshizuka
  • Yukio Ohsawa
  • Sae Kondo

Organizing Committee

  • Agrawal, Jitendra – University of Bristol
  • Auernhammer, Jan– Stanford Univeristy
  • Bandini, Stefania – University of Milano-Bicocca
  • Bewong, Michael – Charles Sturt University
  • Correa da Silva, Flavio – University of São Paulo
  • Dobashi, Masaru, NTT Data Inc., Japan
  • Fruchter, Renate – Stanford University
  • Haller, Stephan ,Bern University of Applied Sciences, Switzerland
  • Jugulum, Rajesh – Northeastern University
  • Kondo, Sae – Mie University / RCAST, University of Tokyo
  • Koshizuka, Noboru – University of Tokyo
  • Nishinari, Katsuhiro – University of Tokyo
  • Licia, Amichi - Oak Ridge National Laboratory
  • Ohsawa, Yukio – University of Tokyo (Chair)
  • Sekiguchi, Kaira – University of Tokyo
  • Shimojo, Shinji ,Aomori University, Japan
  • Seike, Hirotsugu ., The University of Tokyo, Japan
  • Takeda, Hideaki ,National Institute of Informatics, Japan
  • Van den Poel, Dirk – Ghent University
  • Wong, Vivian –University of Florida