Incorporating planning intelligence into deep learning: A planning support tool for street network design
Authors:
- Zhou FangZFZhou Fang
- Ying JinYJYing Jin
- Tianren YangTianren Yang
Preprint
Abstract
Deep learning applications in shaping ad hoc planning proposals are limited by the difficulty in 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, example-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 12 references indexed in Scilit:
- Modelling urban networks using Variational AutoencodersApplied Network Science, 2019
- Land subsidence hazard modeling: Machine learning to identify predictors and the role of human activitiesJournal of Environmental Management, 2019
- Reporting on the Performance and Usability of Planning Support Systems—Towards a Common UnderstandingApplied Spatial Analysis and Policy, 2019
- Urban form and composition of street canyons: A human-centric big data and deep learning approachLandscape and Urban Planning, 2019
- Generative Image Inpainting with Contextual Attention2018
- Globally and locally consistent image completionACM Transactions on Graphics, 2017
- Context Encoders: Feature Learning by Inpainting2016
- Environmental-Sensitive Generation of Street Networks for Traffic Simulations2013
- Visualization of Simulated Urban Spaces: Inferring Parameterized Generation of Streets, Parcels, and Aerial ImageryIEEE Transactions on Visualization and Computer Graphics, 2009
- Procedural modeling of cities2001