Communications of the ACM
Engineers Use AI to Capture Complexity of Breaking Waves
Said MIT's Themis Sapsis, “With this, you could simulate waves to help design structures better, more efficiently, and without huge safety factors.”
Credit: iStockphoto
An international research team led by the Massachusetts Institute of Technology (MIT) leveraged machine learning to model how waves break, which could help improve the design of offshore structures and climate prediction.
The researchers altered traditional equations used to predict wave behavior by combining machine learning and data from wave-tank experiments.
Their model was found to accurately predict how and when waves break, and offered insight into how breaking waves impact the surrounding water.
The model was more accurate than conventional wave equations in estimating a wave's steepness before breaking and its energy and frequency after breaking.
Said MIT's Themis Sapsis, "The number-one purpose of this model is to predict what a wave will do. If you don't model wave breaking right, it would have tremendous implications for how structures behave. With this, you could simulate waves to help design structures better, more efficiently, and without huge safety factors."
From MIT News
View Full Article
Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA
No entries found