Google’s AI model just nailed the forecast for the strongest Atlantic storm this year

In early June, shortly after the start of the Atlantic Hurricane season, Google unveiled a new model designed specifically to predict the tracks and the intensity of tropical cyclones.

Partly of the Google Deepmind suite of meteorological research models based on AI, the “Mether Lab” model for cyclones was a bit unknown for meteorologists when it was launched. In a blog article at the time, Google said its new model, trained on a large set of data that has rebuilt past weather conditions and a specialized database containing key information in the footsteps, intensity and size of hurricanes, had worked well during pre-launched tests.

“Internal tests show that the predictions of our model for the track and the intensity of the cyclone are as precise as the current physics methods,” said the company.

Google said it would join the National Hurricane Center, an arm of the ocean and atmospheric national service that has provided credible forecasts for decades, in order to assess the performance of its meteorological laboratory model in the Atlantic and Eastern Pacific basins.

All eyes on Erin

It had been a relatively calm Atlantic Hurricane season until a few weeks ago, with a global activity below normal levels. There was therefore no high -level tests of the new model. But about 10 days ago, Hurricane Erin quickly intensified in the open Atlantic Ocean, becoming a category 5 hurricane while he followed west.

From a forecast point of view, it was quite clear that Ecrin was not going to hit the United States directly, but meteorologists were transpired details. And because Erin was such a large storm, we had concerns about the proximity of Erin on the east coast of the United States (quite close, it turns out that, a serious erosion of the beach) and its impacts on the small island of Bermuda in the Atlantic.