Forecasting models help us predict when, where and how strongly hurricanes may strike. But such rapid intensification, can elude the predictions of even the best models. Accurately predicting when these violent storms surge and strengthen is an uncertainty within the hurricane forecasting community.
Now thanks to a new model developed by researchers at the Department of Energy’s Pacific Northwest National Laboratory, better predicting hurricane intensity in both the near future and under future climate scenarios is nearly possible. Using artificial intelligence, the team created a model that can, on average, more accurately predict hurricane intensity compared to models used at the national level.
Some hurricane models look at statistical relationships between storm behaviour and locations while others calculate complex motions within Earth’s atmosphere. But like any simulation of an immensely complex system, those models make errors.
To address the weakness of these models, Balaguru and his coauthors developed a deep learning model which detects relationships between hurricane behavior and climate factors like heat stored within the ocean, wind speed and air temperature. The algorithm then forms predictions about which path a storm may take, how strong it could become and how quickly it could intensify.
The team is most excited by the models ability to predict how hurricane behavior may change in different climate scenarios. The new model can generate thousands of simulated hurricanes, offering the chance to better understand how hurricanes evolve in a warmer world.
https://phys.org/news/2021-09-artificial-intelligence-hurricane.html