Deep Umbra: A Generative Approach for Sunlight Access Computation in Urban Spaces
Open Access
- 28 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 11 (2) , 388-401
Abstract
Sunlight and shadow play critical roles in how urban spaces are utilized, thrive, and grow. While access to sunlight is essential to the success of urban environments, shadows can provide shaded places to stay during the hot seasons, mitigate heat island effect, and increase pedestrian comfort levels. Properly quantifying sunlight access and shadows in large urban environments is key in tackling some of the important challenges facing cities today. In this paper, we propose Deep Umbra, a novel computational framework that enables the quantification of sunlight access and shadows at a global scale. Our framework is based on a conditional generative adversarial network that considers the physical form of cities to compute high-resolution spatial information of accumulated sunlight access for the different seasons of the year. We use data from seven different cities to train our model, and show, through an extensive set of experiments, its low overall RMSE (below 0.1) as well as its extensibility to cities that were not part of the training set. Additionally, we contribute a set of case studies and a comprehensive dataset with sunlight access information for more than 100 cities across six continents of the world.Keywords
All Related Versions
Funding Information
- University of Illinois' Discovery Partners Institute
- National Science Foundation (#2320261, #2330565)
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (316963/2021-6)
- Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro (E-26/202.915/2019, E-26/211.134/2019)
- Multicast (MSCA-IF-GF #101028035)
This publication has 46 references indexed in Scilit:
- Mapping the walk: A scalable computer vision approach for generating sidewalk network datasets from aerial imageryComputers, Environment and Urban Systems, 2023
- Generative Adversarial Networks in the built environment: A comprehensive review of the application of GANs across data types and scalesBuilding and Environment, 2022
- Free and open source urbanism: Software for urban planning practiceComputers, Environment and Urban Systems, 2022
- A novel solar envelope method based on solar ordinances for urban planningBuilding Simulation, 2019
- ShadowGAN: Shadow synthesis for virtual objects with conditional adversarial networksComputational Visual Media, 2019
- Modeling the potential for PV installation in residential buildings in dense urban areasEnergy and Buildings, 2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- The residential solar block envelope: A method for enabling the development of compact urban blocks with high passive solar potentialEnergy and Buildings, 2015
- Impact of urban geometry on outdoor thermal comfort and air quality from field measurements in Curitiba, BrazilBuilding and Environment, 2011
- Solar and daylight availability in the urban fabricEnergy and Buildings, 2004