Yuta Sato

Application of Graph Representation Learning for Urban Sustainable Policies

Name: Yuta Sato
Primary Supervisor: Dr. Elisabetta Pietrostefani
Year: 1
Discipline: Geography
Presentation type: 6 Minute talk
Project Title: Application of Graph Representation Learning for Urban Sustainable Policies

Abstract:

Recently, urban planners have been exploring new ways to make cities more livable and sustainable. One key concept is the "15-Minute City," where residents can access their daily needs within a 15-minute walk or bike ride from their homes. Understanding how different parts of a city are connected and function together is crucial for creating policies that improve economic, social, and environmental sustainability. However, we still do not fully understand how neighbourhood configurations and their various functions affect each other. I will propose a new method using artificial intelligence (specifically, a graph neural network) to analyse these relationships within street networks across England and Wales in 2024. This analysis will help us understand how different neighbourhood patterns relate to important factors like carbon emissions, crime rates, and average income.