Incorporating Planning Intelligence into Deep Learning: A Planning Support Tool for Street Network Design
Authors:
- 22 December 2021
- journal article
- research article
- Published by Taylor & Francis in Journal of Urban Technology
- Vol. 29 (2) , 99-114
Abstract
Deep learning applications in shaping ad hoc planning proposals are limited by the difficulty of integrating professional knowledge about cities with artificial intelligence. We propose a novel, complementary use of deep neural networks and planning guidance to automate street network generation that can be context-aware, learning-based, and user-guided. The model tests suggest that the incorporation of planning knowledge (e.g., road junctions and neighborhood types) in the model training leads to a more realistic prediction of street configurations. Furthermore, the new tool provides both professional and lay users an opportunity to systematically and intuitively explore benchmark proposals for comparisons and further evaluations.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Procedural Urban Modeling of Population, Road Network and Land UseTransportation Research Procedia, 2015
- Transit Deserts: The Gap between Demand and SupplyJournal of Public Transportation, 2013
- Mining urban land-use patterns from volunteered geographic information by means of genetic algorithms and artificial neural networksInternational Journal of Geographical Information Science, 2012
- Authoring Hierarchical Road NetworksComputer Graphics Forum, 2011
- Procedural Generation of RoadsComputer Graphics Forum, 2010
- Interactive procedural street modelingACM Transactions on Graphics, 2008
- CREATING MORE PEOPLE-FRIENDLY URBAN STREETS THROUGH ‘LINK AND PLACE’ STREET PLANNING AND DESIGNIATSS Research, 2008
- Procedural modeling of cities2001
- Image inpainting2000
- Locational Models, Geographic Information and Planning Support SystemsJournal of Planning Education and Research, 1993