Lab

Digital City Science


About the lab

Digital City Science at HCU explores urban complexity with digital technologies. Our team develops scientific new approaches for the analysis and integrative planning of urban systems. For this purpose, the team comprises expertise in architectural design, urban and spatial planning, media technology, IT, and software development, among others. In cooperation with partners from academia, business, administration, and civil society, we develop data-based tools and methodologies that are applied in the national and international context. Our scientific activities span from fundamental research across applied projects to knowledge transfer in scientific teaching and training.

Featured research (7)

In the realm of Artificial Intelligence (AI) and Machine Learning (ML), the scarcity of robust and diverse datasets often poses a significant challenge, prompting the need for effective data generation methods. This paper presents an evaluation of tabular data generation techniques on the DaFne platform, centered around a predictive maintenance case study for bridges. The DaFne platform offers a variety of tabular data generation functionalities, including rule-based creation, data fusion (with weather data), and data reproduction. We investigate the utility of these functionalities across different Machine Learning models for the prediction of bridge conditions. Our analysis includes a descriptive statistical comparison of real and synthetic data. Additionally, we explore the utility of original, weather, and synthetic datasets. We do this through the lens of ML models like MLR, XGBoost, CNN, and GRU, performing a predictive maintenance algorithm on these datasets. Our results indicate that while the inclusion of weather data did not significantly enhance predictive performance, the synthetic dataset shows satisfactory quality. However, the synthetic data’s performance is lower than the original data in predictive maintenance tasks, with differences observed in models heavily reliant on sequential data. This research underscores the potential of the DaFne platform in generating high-quality synthetic data. It also highlights areas for future improvement and offers valuable insights for advancing data generation and analysis techniques in predictive maintenance and other AI applications.
AI integration in Smart Cities, primarily through agent-based simulations, holds transformative potential for understanding and enhancing citizen behavior. Striking a balance between complexity and computational feasibility is essential. Our research question is, how can we make agents behave more realistically? We assumed that happiness is a motivating factor for the mobility. Insights from a survey of 130 citizens inform our weightings. We used reinforcement learning (RL) as a method and Q-learning as an algorithm to generate a baseline, further enhanced with neural networks for adaptability. This study contributes to data-driven urban design by offering efficient intelligent agent solutions. The research lays foundations for smart agents in urban design, which can be used to generate synthetic data.
In today's globalized world, cross-cultural settings, projects, and institutional setups are becoming increasingly common, presenting both opportunities and challenges. Knowledge creation and management plays a critical role in addressing these challenges by facilitating the sharing of information, ideas, and best practices across different cultures and contexts. However, effective knowledge creation and management in cross-cultural settings requires a nuanced understanding of different cultures, as well as a recognition of the potential barriers to communication and collaboration. One specific area where knowledge generation and management is of particular importance is sustainable development in the built environment. As the world's population continues to grow and urbanization accelerates, sustainable development is increasingly recognized as a critical challenge that requires urgent action. To address this challenge, knowledge creation and management approaches that can facilitate the exchange of ideas, best practices, and innovative solutions are essential. However, effective knowledge creation and management in this context requires an understanding of the unique cultural, social, and economic factors that shape different communities' perspectives on sustainability. Against this backdrop, this paper presents the set-up of the SURE Facilitation and Synthesis Research Project, focusing on the conceptual architecture for its synthesis research. Part of the BMBF funding initiative SURE along with the ten collaborative projects, this project facilitates the synthesis of knowledge about and the development of solutions for sustainable and resilient urban and rural development in Southeast Asia and China. The project focuses on the transdisciplinary synthesis of research outputs from the SURE collaborative projects, the identification of research gaps, and the development of knowledge generation and management approaches to support the implementation of sustainable solutions, while its primary goal is to contribute to transdisciplinary knowledge synthesis, sustainability research, and urban research. The project focuses on utilizing a multi-method approach that combines empirical research with artificial intelligence tools to analyse qualitative and quantitative data. The project team employs digital tools to structure data and turn it into accessible knowledge that can be used in transdisciplinary urban sustainability projects and beyond. The overarching goal of the project is to contribute to a new research approach that synthesizes knowledge in the topic area of urban sustainability.
This paper reports on results of the SURE facilitation and synthesis research (FSR) project for the funding priority SURE (Sustainable Development of Urban Regions) of the German Federal Ministry of Education and Research (BMBF). SURE engages ten collaborative projects which develop concepts and test locally implementable solutions and strategies for sustainable transformation of fast-growing urban regions in Southeast Asia and China. SURE aims to create conceptual, theoretical, methodological, and translational innovations that integrate and move beyond discipline-specific approaches to address issues of sustainable urban development. The paper discusses the application of Natural Language Processing (NLP) as one form of Artificial Intelligence (AI) to support data and knowledge synthesis in sustainable urban development research. The abundant urban data and recent advancements in the field of AI have the potential to transform how urban researchers perceive and tackle sustainable development-related problems of cities. The research team employs various NLP algorithms to assess text data with the goal to analyse patterns in order to explore intra-project synergies and research intelligence on future trends. NLP has exhibited an ability to digest copious textual data and improve the usability of urban corpora, improving study scope and reducing resources required for research. However, the implementation of NLP to study issues related to sustainable urban development is a relatively novel. Predominantly used NLP modules are unable to identify contextual relations amongst multiple words which is essential in urban region study. To overcome this issue, algorithms employed were trained to identify various word classifications related to urban study discipline for precise output. We discuss the preliminary results of the ongoing exploration and show how it could contribute to an understanding of large text-based data sets in urban knowledge management. We examine the possibilities and limitations of such an approach and discuss the implications of AI as part of a multi-methodological approach to carry out a synthesis of sustainable urban development research efforts across an entire region covered under SURE framework. The paper also gives an outlook on utilising new AI based algorithms to generate text-based data analysis channel as well as indicate the limits, successes, challenges and constraints of such approaches.

Lab head

Jörg Rainer Noennig
Department
  • Digital City Science

Members (15)

Ayse Glass
  • HafenCity University Hamburg
Maria Moleiro Dale
  • HafenCity University Hamburg
Burak Bek
  • HafenCity University Hamburg
Agota Barabas
  • HafenCity University Hamburg
Arjama Mukherjee
  • HafenCity University Hamburg
Mehmet Akif Ortak
  • Istanbul Technical University
Xingyue Wang
Xingyue Wang
  • Not confirmed yet
Juan Hernandez
Juan Hernandez
  • Not confirmed yet
Göktürk Köse
Göktürk Köse
  • Not confirmed yet
Jennifer Jiang
Jennifer Jiang
  • Not confirmed yet

Alumni (7)

Jesús López Baeza
  • HafenCity University Hamburg
Niloufar Vadiati
  • HafenCity University Hamburg
Rafael Milani Medeiros
  • HafenCity University Hamburg
Andre Landwehr
  • HafenCity University Hamburg