ITU Research Presented at AESOP 2025: A Data-Driven Approach to the 15-Minute City

A research team from Istanbul Technical University (ITU) contributed to the academic programme of the AESOP Annual Congress 2025, held between 7–11 July 2025 at Yıldız Technical University, Istanbul, by presenting a study focused on pedestrian accessibility within the framework of the 15-minute city.

The paper, titled “Performance Analysis of 15-Minute City Zones Through Spatial and Machine Learning Techniques,” was presented by Aydın Furkan Terzi as part of the congress sessions. The study was co-authored by Aydın Furkan Terzi, Ayşenur Koçyiğit, Koray Aksu, and Prof. Dr. Hande Demirel, representing Istanbul Technical University.

The research proposes a comprehensive methodology to assess pedestrian accessibility in metropolitan contexts, with a specific focus on Küçükçekmece District in Istanbul. Moving beyond traditional distance-based accessibility measures, the study integrates spatial clustering techniques, slope-adjusted walking speeds, and categorized point-of-interest (POI) data to provide a more realistic evaluation of daily accessibility conditions.

A key methodological contribution of the study is the application of the Mean Shift clustering algorithm, a machine learning-based approach used to identify accessibility clusters without predefined assumptions. Accessibility performance was evaluated across 15-, 20-, and 25-minute walking thresholds, allowing for a comparative analysis of spatial inequalities and service reach within the urban fabric.

By incorporating topographic constraints and differentiated POI categories, the research highlights how urban form, terrain, and land-use distribution shape walkability outcomes in dense metropolitan areas. The findings contribute to ongoing academic and policy discussions on human-scale urban planning, sustainable mobility, and data-driven spatial analysis.

The presentation at AESOP 2025 supports the Forthcoming project’s dissemination and knowledge-sharing objectives, reinforcing the role of advanced spatial and analytical methods in understanding and improving urban accessibility. It also demonstrates how machine learning techniques can be effectively integrated into urban planning research to inform more inclusive and resilient city strategies.