NASA-funded wildfire digital twin could save assets and lives with pollution prediction, burn forecasting

One year ago, the Palisades and Eaton Fires ravaged the coast of Southern California. Combined, the fires killed 28 people, destroyed more than 16,000 structures, and displaced tens of thousands of residents.

Wildfires are notoriously difficult to predict due to the multitude of factors that affect their growth, spread, and speed. That uncertainty makes it difficult for response teams to know who should be evacuated to avoid both active flames and hazardous air pollution. Mass evacuations require cooperation and communication across numerous departments, and getting those systems activated can take precious time that evacuees might not have if the fire is spreading at a rate of seven and a half football fields per minute as the Palisades fire did.

One researcher at George Mason is working on a solution. Chaowei "Phil" Yang, professor in the Geography and Geoinformation Science Department in the College of Science, has teamed up with researchers from California State University-Los Angeles (CSU-LA), NASA Jet Propulsion Laboratory, and the City of Los Angeles to develop a wildfire digital twin to understand fire evolution and air pollution impact.

"The goal is to develop an artificial intelligence (AI)-based system that can provide real-time, high-resolution simulation and forecasting of wildfire behavior and model the resulting air pollution and air quality impacts for better informed public health responses," Yang said.

Air pollution is a critical metric here. "Inhaling wildfire smoke can cause serious and long-lasting damage to the breathing system," said Yang. "We need to get those people impacted to safety as well as those in direct line of the spreading flames."

Yang, who is the director of the Center for Intelligent Spatial Computing for Water/Energy Science, has worked on several projects using his knowledge of geospatial cyberinfrastructure and spatial cloud computing to study the impacts of major global events on air quality. When the wildfires hit southern California, Yang felt that his expertise and resources could be used to help mitigate future wildfire disasters.

Yang's work ties directly to improving human health, well-being, and preparedness, as well as building a climate-resilient society, two key solutions in George Mason's Grand Challenge Initiative, the university's research focus to enable us to live in a world of our choosing.

"Looking at the damage increasing because of climate change, to both assets and people's life and health, that really triggered us," Yang said. "We really felt that we needed to do something to address it."

The digital twin will integrate a range of data from a diverse set of sources-such as satellites, UAVs, ground observations, and citizen reports-in order to forecast and simulate the progress of a wildfire and the mitigation of potential interventions. Everything from fuel sources, moisture, load, and consumption to wind speeds and temperatures to real-time sensors for the fire are pulled into the system.

George Mason's high-performance computing (HPC) cluster is used to automate the data interpretation process, while machine learning modeling calibrates the data sets to increase accuracy. As more data sets become available, the model's accuracy will increase.

"When we eventually provide information to firefighters and local agencies, we will give them a range of possibilities and a confidence level in those possibilities, such as 'the fire will move in this direction with about 90% confidence, or 20% confidence,'" Yang explained. "That's important for them when they're trying to make these quick decisions about where to put fire fighters. It makes the information actionable instead of just data sets."

While working on a bold solution to a grand challenge, the project is also an opportunity for students of all levels-from high school through post-doctoral-to get hands-on experience in cloud computing and digital transformation to address grand challenges.

Anusha Srirenganathan, PhD Earth Systems and Geoinformation Sciences '25, joined the project during her time at George Mason. "Working closely with researchers from different disciplines helped me grow as a collaborator, and my work on the project strengthened my abilities in large-scale satellite data processing, spatial cloud computing, and AI/ML modeling for environmental applications," she said.

"We're using these capabilities to cultivate the next generation workforce," said Yang. "It's eye-opening for the students and paves a path for them to become the future leaders of the nation."

Securing a safer future for both the current and future generations is what drives Yang in his work. And he sees this work on a wildfire digital twin as only the beginning of what's possible with the technology.

Yang said his team is already working on a Chesapeake Bay digital twin project to develop more accurate flood forecasting, and collaborating with Daniel Rothbart at the Carter School on a conflict resolution digital twin with an alert system. "There could be possibilities for this technology to help predict other natural disasters or forecasting conflict as it evolves," Yang said. "It's exciting to get the chance to utilize our knowledge and tools to address the grand challenges we're facing today to hopefully save lives and reduce asset loss."

"This experience has shown me that research can provide real value when it matters most," Srirenganathan said.

Learn more about the College of Science

Related news

Topics