Urban informatics: Systems science and machine learning in spatiotemporal analysis

Urban planning as a discipline has struggled with efficient ways to integrate new technologies into planning processes. The main challenges can be traced to some fundamental weaknesses in planning technology design, development, and implementation. For example, a lack of flexibility in tool design and a lack of open and transferable data sources and collection methods. To date, there have also been poor user interactions in both technology development and use. Finally and perhaps most importantly, there has been a distinct inability to reliably replicate and adapt urban decision support models across contexts (from one place to another). There have been many high-quality models built for specific places that cannot be replicated or used anywhere else. Opportunities in big data and smart technologies offer some promise for improving and addressing these weaknesses. Many of these opportunities, however, emphasize advanced information technology, rather than the integration of the technique into actual decision-making processes, making them less useful in the world of practical planning. This dissertation explores ways in which big data, ubiquitous computational technology, and digital social networks, can contribute to addressing the challenges that hamper the adoption of planning technologies and implementation of planning support systems (PSS) more directly. Under the lexicon of ‘Urban Informatics’, this work aims to enable a new generation of planning technologies more readily integrated within the plan-making process and in the process affecting better urban planning decisions in more places.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Informatics

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2022

Author dc:creator

• Chen, Si

Contributors dc:contributor

• Deal, Brian
• Wilson, Bev
• Cidell, Julie
• Wang , Shaowen

• Urban informatics
• Machine learning
• Model cross-domain adaptation
• Interactive interface
• Social media

Statement dc:rights

• Copyright 2022 Si Chen

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/115686

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F115686