At the 2024 Parish Games, the marathon pushed through miles of scorched pavement, and fans crammed into sun-stained squares and stadiums. Over a year later, fans remember the fun and fashionable game. But for event staff, the calm challenge of extreme heat planning remains.
Shades are essential when mercury rises. Shadows from buildings can lower surface temperatures above 20 degrees Fahrenheit, providing life-saving relief. But knowing where the shade is and how to get there isn't always easy.
So, Hua Wei and his team at Arizona State University believe artificial intelligence, or AI, can help.
Why this research is important
Research is an invisible hand that promotes American progress. Unlock discovery and create opportunities. Develop new technologies and new ways to do things.
Learn more about the ASU discoveries that contribute to global change and the world's leading economic forces by studying America.
Wei, an assistant professor of computer science and engineering for computing and augmented intelligence, part of ASU's IRA A. Fulton Schools of Engineering Schools, has launched two complementary projects that use AI to make shade information practical, accessible and practical.
One can help you choose a cooler walking or cycling route in real time. The other uses the generator AI to simulate how shades shift into one day, providing data to urban planners and designers. Together, the project is part of Wei's broader mission. Use AI to support smart, human-centered cities.
Stay cool while traveling
The first project, called Shaded Route Planning, was designed especially with pedestrians and cyclists in mind who will be exposed to hours of sun during heat waves. Traditional mapping apps prioritize speed or distance. Wei's tool adds a third element: Shade.
The system starts by scanning satellite images to find places where the shade falls from trees, buildings, or other structures. Then, line up that information on sidewalks and street maps to see how much of each path is covered. From there, the tool offers users several options. They can take the fastest, the most shadowy route, or balance between the two.
This prototype was successfully tested at the Parish Games, allowing visitors to choose cooler passes between venues. In the demonstration, the shortest route glowed orange across the map, cutting straight through the sun-drenched highway. A slightly longer journey appears in the greenery, winding down shaded alleys and tree-lined paths.
“Slight changes to the route can make a huge difference,” says Wei. “That could mean a much more enjoyable experience with fewer cases of fever fatigue for thousands of travelers.”
Today I'm looking at the shadow of tomorrow
Shade route planning is useful for people on the move, but Wei's second project looks at the big picture. Deepshade is a generic AI system that predicts how shade will appear and how urban shifts will appear.
The problem is that normal satellite photos do not clearly show the shade. When the shadows may look completely different, they may be outdated, rough, or inconsistent. Deepshade fixes this by creating realistic “What-if” photos of shadows all day and throughout the season. Use information about the building and the location of the sun to simulate how the shade falls. These examples teach AI systems how to generate detailed shade maps in a way that is in demand. Users can ask the system to show, for example, what it will look like at 6pm in July.
To improve accuracy, the model uses edge detection to capture learning in contrast to crisp building outlines, allowing shadows to evolve realistically over time. In experiments in 12 cities, from Beijing to Tempe, Arizona, deep shades consistently outperformed other AI methods in generating accurate shade predictions.
In reality, this means that city planners can use deep shades to test how to add rows of trees, adjust building heights, and place new bus stops. It offers a “cool hallway” and a data-driven way to design public spaces that protect vulnerable groups during extreme heat.
Animated graphics showing deep shades. The system employs noisy satellite images and uses AI to generate realistic, high-resolution shade maps. Data Mining and Reinforcement Learning Group/ASU Graphics Provided
The rising researcher
For WEI, these projects are part of a growth portfolio of work that combines technical AI expertise with real impact. His research into decision-making systems has already won the prestigious 2025 National Science Foundation Foundation Early Career Development Program, or careers, awards, support from Amazon, and collaborations with city government.
He specifically focuses on what AI researchers call the “simulation-reality gap,” or the problems that stumble upon real-world conditions, where algorithms often work well in clean, simulated environments, but cluttered and unpredictable. Shades depend on the weather, seasons and city shape, making them a perfect example of this complexity.
To tackle these challenges, WEI works closely with other leading researchers, including Yezhou “YZ” Yang, an associate professor of computer science and engineering. Yang is a thought leader in computer vision and has become the ideal collaborator for projects such as Deep Shade.
“For me, AI's promise has always been more than an algorithm: creating tools that can be exposed to people's lives in meaningful ways,” says Yang. “I have long believed that Social Good's AI means not only advancing technology, but also designing systems that bring comfort, dignity and happiness to the communities we serve.”
Design not only for systems but for people
Heartily, Wei's job is to empower people. When extreme heat becomes one of the world's most looming public health challenges, tools like shaded route planning and deep shade are more than technical experiments. They get a glimpse into how the city adapts – not in an abstract way, but rather a glimpse of cyclists finding relief under wooden covers, tourists enjoying a cool walk to the Olympic venue, or community planners who decide where to add their next green stretch.
“We want AI to support decisions that people can feel in their daily lives,” says Wei. “When the sun is falling, finding shade isn't just about comfort. It's about health and resilience.”
