Flood under the Old Route 49 bridge crossing over the South Yuba River in Nevada City, California. Credit: Kelly M. Grow/ California Department of Water Resources
A new machine learning tool can reduce errors in national flood prediction programing, resulting in more accurate predictions of where floods will occur. In a new study, scientists found that when the AI was used in combination with the National Water Model, developed by the U.S. National Oceanic and Atmospheric Administration, the resulting hybrid model was four to six times more accurate. The AI was trained on NOAA data for the United States, but the system can be specialized for any country.
The study was published in AGU Advances, which publishes high-impact, open-access research and commentary across the Earth and space sciences.
This AI is a neural network, or a deep learning model, and is trained to find errors. The network was trained on historical observational and National Water Model simulated data on rainfall and flooding. Researchers created a hybrid program by combining the AI system with the National Water Model, which forecasts streamflow for the entire United States.
"So especially for floods, the performance of the pure AI model is quite poor," said Vinh Ngoc Tran, hydrologist at the University of Michigan and head researcher on the study. "The advantage of the AI model is that they are very simple. You only need to use the data to train the model and provide the forecast, but the most important thing we need to be concerned about is ensuring prediction accuracy for flood events that can cause significant damage."
Across the United States, NOAA has nearly 11,000 operational water gauges that collect data on previous floods and water levels, but NOAA also keeps track of other data than just water. The agency gathers detailed information on variables such as vegetation, urbanization, and drainage networks for the different gauges.
Interactive NOAA map of the National Water Model. Each colored dot is a water gauge that has information on flood potential. Credit: NOAA
The sheer amount of available information is helpful, but it also makes it harder to narrow down the research to figure out where things went wrong or to simply account for everything when creating a flood model. This will cause errors in the forecasting system, and that is where AI can step in.
Aptly named Errorcastnet, the AI-based system looks for errors in the national model. It looked at old floods and what the model forecasted for the floods. For times when NOAA's model did not correctly forecast the flood, the AI would categorize the errors into two groups: the errors it could reduce and those that could simply not be fixed.
The AI learns the problems within the model and works to correct them. The errors that cannot be fixed, like limitations within the model itself or incomplete data, are still important to track. It helps the AI continue to train and improve the forecasting by focusing only on the errors that it can fix.
"You can't throw away physics," said Valeriy Ivanov, physical hydrologist at the University of Michigan and an author of the study. "It's just by definition you can't. You have to understand that systems are different. The landscapes are different. You have to account for dominant physical processes in your predictive model."
Researchers found that when only using Google's AI flood forecasting program, which uses historical data to make predictions but doesn't consider details such as elevation, vegetation, and reservoirs that National Water Model incorporates, the model would generally underpredict flood flows.
"We understand the power of AI," Ivanov said. "No one denies it. It's definitely there. But it should not negate decades of research. It should not negate the understanding of physics and understanding of complexity of physical processes in watersheds."
By bettering NOAA's forecasting model, the researchers said they think it could also improve the potential economic impacts of floods. More accurate flood predictions could mean businesses can better prepare for the coming floods. Tran, Ivanov and their team hope that as the program grows, potential floods could be predicted in detail up to several days or more before they happen.
Notes for journalists:
This study is published in Earth's Future, an open-access AGU journal. View and download a pdf of the study here. Neither this press release nor the study is under embargo.
Paper title:
"AI Improves the Accuracy, Reliability, and Economic Value of Continental-Scale Flood Predictions"
Authors:
- Vinh Ngoc Tran, Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor, Michigan, USA
- Taeho Kim, Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor, Michigan, USA
- Doughui Xu, Atmospheric, Climate, & Earth Sciences Division, Pacific Northwest National Laboratory, Richland, Washington, USA
- Hoang Tran, Atmospheric, Climate, & Earth Sciences Division, Pacific Northwest National Laboratory, Richland, Washington, USA
- Manh-Hung Le, NASA Goddard Space Flight Center, Greenbelt, Maryland, USA
- Thanh-Nhan-Duc Tran, Department of Civil and Environmental Engineering, University of Virginia, Charlottesville, Virginia, USA
- Jongho Kim, School of Civil and Environmental Engineering, University of Ulsan, Ulsan, South Korea
- Trung Duc Tran, School of Civil and Environmental Engineering, University of Ulsan, Ulsan, South Korea
- Daniel Wright, Department of Civil and Environmental Engineering, University of Wisconsin-Madison, Madison, Wisconsin, USA
- Pedro Restrepo, Minneapolis, Minnesota, USA
- Valeriy Ivanov, Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor, Michigan, USA
AGU (www.agu.org) is a global community supporting more than half a million professionals and advocates in Earth and space sciences. Through broad and inclusive partnerships, AGU aims to advance discovery and solution science that accelerate knowledge and create solutions that are ethical, unbiased and respectful of communities and their values. Our programs include serving as a scholarly publisher, convening virtual and in-person events and providing career support. We live our values in everything we do, such as our net zero energy renovated building in Washington, D.C. and our Ethics and Equity Center, which fosters a diverse and inclusive geoscience community to ensure responsible conduct.
#
Contributed by Riley Thompson
