Raging wildfires occurring worldwide have caused tremendous economic damage and loss of life. Knowing in advance when and where a widespread fire could strike can improve fire prevention and resource allocation. However, available forecasting systems provide only limited information. Additionally, they don’t provide long enough lead times to get useful regional details.
Scientists have now applied a deep learning algorithm to improve forecasting of wildfire danger in the western United States. Researchers from South Korea and the United States have developed a hybrid method combining AI techniques and weather forecasting to produce improved forecasts of extreme fire hazards up to a week at finer scales (4km x 4km resolution) and their usefulness for firefighting and to increase management.
“We have tried numerous approaches to integrate machine learning with traditional weather forecasting models to improve wildfire risk predictions. This study is a major step forward as it demonstrates the potential of such an effort to improve fire hazard prediction without the need for additional computing power.” says lead author Dr. Rackhun Son, a recent PhD Dr. from the Gwangju Institute of Science and Technology (GIST) in South Korea, who is currently working at the Max Planck Institute for Biogeochemistry in Germany. “Fire hazard predictions could be further improved through continued refinement of both Earth system models and recent AI developments,” he adds.
While data-driven AI methods have shown excellent ability to infer things, explaining why and how the inferences are arrived at still remains a challenge. This has led to AI being referred to as a black box. “But when AI was combined with computer models based on physical principles, we were able to diagnose what was going on in that black box.” says co-author Prof. Simon Wang from Utah State University, USA. “The AI-based predictions related to extreme fire hazards are well grounded on strong winds and specific geographic features, including high mountains and canyons Western United States, which have traditionally been difficult to solve with coarser models.”
Computational efficiency is another major advantage of this method. Traditional methods of predicting fire risks at finer spatial resolutions, a process known as “regional downscaling,” are often computationally intensive, expensive, and time-consuming. “Although comparable computational resources were required during the development phase, once the training task for the AI was complete, i.e. performed once, it took only a few seconds to use this component with the weather forecast model to produce forecasts for the rest of the season, “ says co-author Prof. Kyo-Sun Lim from Kyungpook National University, Korea. Therefore, the newly developed AI-based method, with the ability to produce accurate high-resolution predictions in less time, was much more cost-effective compared to traditional prediction systems.
“In this study, AI is only tested for predicting fire hazards in the western United States. In the future it could be applied to other types of weather extremes or to other parts of the world.” said co-author Dr. Philip J. Rasch of the Pacific Northwest National Laboratory and the University of Washington. “The flexibility of our AI method can help predict any weather-related feature.”
The research was published in the Journal of Advances in Modeling Earth Systems on September 22, 2022.
Authors: Rackhun Son1.8, Po Lun Ma2Hailong Wang2Philip J. Rasch2.3Shih Yu (Simon)5 Wang4Hyung Jun Kim5,9,10Jee Hoon Jeong6Kyo Sun Sunny Lim7Jin Ho Yoon8th,
1 Department of Biogeochemical Integration, Max Planck Institute for Biogeochemistry
2 National Laboratory of the Pacific Northwest
3 Department of Atmospheric Sciences, University of Washington
4 Department of Plants, Soils and Climate, Utah State University Logan
5 Moon Soul Graduate School of Future Strategy, Korea Advanced Institute of Science and Technology
6 Faculty of Earth and Environmental Sciences, Chonnam National University
7 School of Earth System Science, Kyungpook National University
8th School of Earth Sciences and Environmental Engineering, Gwangju Institute of Science and Technology
9 Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology
10 Institute of Industrial Sciences, University of Tokyo
About Gwangju Institute of Science and Technology (GIST)
The Gwangju Institute of Science and Technology (GIST) is a research-oriented university in Gwangju, South Korea. Established in 1993, GIST has grown into one of the most prestigious schools in South Korea. The University aims to create a strong research environment to drive advances in science and technology and encourage collaboration between international and national research programs. With its motto “A Proud Creator of Future Science and Technology,” GIST has consistently received one of the highest university rankings in Korea.
About the author
Jin-Ho Yoon is Professor of Geosciences and Environmental Engineering at GIST, Korea. His group focuses on understanding and predicting weather-climate extremes under climate change. Prof. Yoon’s group also analyzes interactions between aerosols, clouds and precipitation to understand the distribution and properties of clouds. Before joining GIST, he was a scientist (level 3) at the Pacific Northwest National Laboratory. In 2004, Prof. Yoon received a Ph.D. in Atmospheric Sciences from Iowa State University, USA.
Journal of Advances in Modeling Earth Systems
subject of research
Deep learning provides significant improvements for county-level fire weather forecasting in the western United States
Article publication date
September 22, 2022
Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of the press releases published on EurekAlert! by contributing institutions or for the use of information about the EurekAlert system.