Deep Umbra: A Generative Approach for Sunlight Access Computation in Urban Spaces
IEEE Transactions on Big Data, 2025
Skip to content
Deep Umbra
A Generative Approach for Sunlight Access Computation in Urban Spaces
Generative approach for city-scale shadow computation
Deep Umbra is a novel computational framework that enables the quantification of sunlight access and shadows at a global scale. Our framework is based on a 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. Deep Umbra's primary motivation is the impact that shadow management can have in people's quality of life, since it can affect levels of comfort, heat distribution, public parks, etc.
We also present the Global Shadow Dataset, a comprehensive dataset with the accumulated shadow information for over 100 cities in 6 continents. Download the data, or explore it in the web viewer.
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 environment, shadows can provide shaded places for stay during the hot seasons, prevent heat island effect, and increase the pedestrian level of comfort. 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 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. We also contribute a set of case studies and a comprehensive dataset with the sunlight access information for more than 100 cities throughout six continents of the world.
Publications
Team
- Kazi OmarUniversity of Illinois Chicago
- Gustavo MoreiraUniversity of Illinois Chicago
- Daniel HodczakUniversity of Illinois Chicago
- Maryam HosseiniUniversity of California, Berkeley
- Marcos LageUniversidade Federal Fluminense
- Fabio MirandaUniversity of Illinois Chicago
How to cite
@article{omar2025deepumbra,
title = {Deep Umbra: A Generative Approach for Sunlight Access Computation in Urban Spaces},
volume = {11},
doi = {10.1109/tbdata.2024.3382964},
number = {2},
journal = {IEEE Transactions on Big Data},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
author = {Omar, Kazi Shahrukh and Moreira, Gustavo and Hodczak, Daniel and Hosseini, Maryam and Colaninno, Nicola and Lage, Marcos and Miranda, Fabio},
year = {2025},
month = apr,
pages = {388--401},
eprint = {2402.17169},
archiveprefix = {arXiv}
}