Modeling urbanization patterns with generative adversarial networks

2018/01/08 by Albert, Adrian, Strano, Emanuele, Kaur, Jasleen +1 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.1801.02710

Abstract

In this study we propose a new method to simulate hyper-realistic urban patterns using Generative Adversarial Networks trained with a global urban land-use inventory. We generated a synthetic urban "universe" that qualitatively reproduces the complex spatial organization observed in global urban patterns, while being able to quantitatively recover certain key high-level urban spatial metrics.

Cited by

• Generative AI for Urban Design: A Stepwise Approach Integrating Human Expertise with Multimodal Diffusion Models

Related

• Re-designing cities with conditional adversarial networks
• Automated Urban Planning for Reimagining City Configuration via Adversarial Learning: Quantification, Generation, and Evaluation
• Automated Urban Planning aware Spatial Hierarchies and Human Instructions
• Spatial sensitivity analysis for urban land use prediction with physics-constrained conditional generative adversarial networks
• City Street Layout Generation via Conditional Adversarial Learning