Modeling urbanization patterns with generative adversarial networks

01/08/2018

∙

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.

READ FULL TEXT

Modeling urbanization patterns with generative adversarial networks

Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks

Spatial sensitivity analysis for urban land use prediction with physics-constrained conditional generative adversarial networks

Prediction of Transportation Index for Urban Patterns in Small and Medium-sized Indian Cities using Hybrid RidgeGAN Model

Analysis of the use of smart cards on the urban railway

MetroGAN: Simulating Urban Morphology with Generative Adversarial Network

Predicting Rapid Fire Growth (Flashover) Using Conditional Generative Adversarial Networks

Re-designing cities with conditional adversarial networks

Modeling urbanization patterns with generative adversarial networks

Related Research

Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks

Spatial sensitivity analysis for urban land use prediction with physics-constrained conditional generative adversarial networks

Prediction of Transportation Index for Urban Patterns in Small and Medium-sized Indian Cities using Hybrid RidgeGAN Model

Analysis of the use of smart cards on the urban railway

MetroGAN: Simulating Urban Morphology with Generative Adversarial Network

Predicting Rapid Fire Growth (Flashover) Using Conditional Generative Adversarial Networks

Re-designing cities with conditional adversarial networks