Machine Learning Approaches for Designing Sustainable Planning Regulations

Forster, Julia and Bindreiter, Stefan (2025) Machine Learning Approaches for Designing Sustainable Planning Regulations. URBAN INNOVATION: TO BOLDLY GO WHERE NO CITIES HAVE GONE BEFORE. Medium sized cities and towns as a major arena of global urbanisation. Proceedings of REAL CORP 2025, 30th Intl. Conference on Urban Development, Regional Planning and Information Society. pp. 1147-1152. ISSN 2521-3938

Text (Machine Learning Approaches for Designing Sustainable Planning Regulations) CORP2025_39.pdf - Published Version Download (1MB)

Abstract

Quantitative and qualitative assessment is essential for identifying levers for sustainable development processes and the impact of planning decisions. Small and medium-sized municipalities in particular struggle with a lack of resources and expertise in the creation and preparation of strategic, forward-looking decision-making bases. AI promises to help automate some of these processes, create a data base and provide planning support that will save time and money in the longrun. This paperillustrates the possibilities of Machine learning (ML) approaches to evaluate quantitative data for qualitative outcomes within planning and decision processes. Furthermore, it provides a basis for discussing possible implications for planning practice based on ML approaches dealing with the impact prediction of planning regulations. In which planning steps and processes can the use of ML bring added value? Which questions can be answered and which prerequisites need to be created? How reliable are results and what can be derived from them? In answering those questions, a special focus will be placed on the needs of small and medium-sizedmunicipalities. The use of the technologies in early planning phases will be analysed, to allow assessment for holistic sustainable developments., in terms of environmental, economic, social and design aspects. ML approaches enable impact prediction based on impact assessment of past regulatory frameworks. Within planning processes, ML-based analysis and predictions allow informed decisions to be made that have analysed future effects and interactions and take holistic considerations into account. AI and big data make it possible to tap into ‘new data sources’ with a view to evaluating and predicting future developments, with the aim of making more resilient planning decisions. This changes the role of planning, as it is all the more required to help interpret the data and draw the right conclusions for future measures and solutions.

Item Type:	Article
Uncontrolled Keywords:	small and medium-sized municipalities, decision support, planning regulations, machine learning, planning
Subjects:	J Political Science > JS Local government Municipal government T Technology > T Technology (General) T Technology > TA Engineering (General). Civil engineering (General)
Depositing User:	The CORP Team
Date Deposited:	25 May 2025 15:36
Last Modified:	07 Jul 2025 09:31
URI:	http://repository.corp.at/id/eprint/1233

Actions (login required)

View Item