The 2025 hurricane season officially begins on June 1, and it's forecast to be more active than ever, with potentially devastating storms whose heavy rainfall and powerful storm surges cause dangerous coastal flooding.
The 2025 hurricane season officially begins on June 1, and it's forecast to be more active than ever, with potentially devastating storms whose heavy rainfall and powerful storm surges cause dangerous coastal flooding.
Extreme water levels — like the 15 feet of flooding Floridians saw during Hurricane Helene in 2024 — threaten lives, wash away homes, and damage ecosystems. But they can be difficult to predict without complex, data-intensive computer models that areas with limited resources can't support.
A recent study published in Water Resources Research by civil and environmental engineering graduate student Samuel Daramola, along with faculty advisor David F. Muñoz and collaborators Siddharth Saksena, Jennifer Irish, and Paul Muñoz from Vrije Universiteit Brussel in Belgium, introduces a new deep learning framework to predict the rise and fall of water levels during storms — even in places where tide gauges fail or data is scarce — through a technique known as “transfer learning.”
The framework, called Long Short-Term Memory Station Approximated Models (LSTM-SAM), offers faster and more affordable predictions that enable smarter decisions about when to evacuate, where to place emergency resources, and how to protect infrastructure when hurricanes approach. For emergency planners, local governments, and disaster response teams, it could be a game-changer — and could save lives.
Read more at Virginia Tech
Image: (From left) Samuel Daramola and David Munoz analyze water level data to better predict future storms. (Credit: Photo by Peter Means for Virginia Tech)
