❌

Normal view

Received yesterday β€” 13 June 2025

Google DeepMind is sharing its AI forecasts with the National Weather Service

12 June 2025 at 17:35

Here's an AI-government collaboration of a less… unsettling variety than some. Google DeepMind is teaming up with the National Hurricane Center (NHC) for tropical cyclone season. The AI research lab claims it can predict hurricane paths and intensities with at least the same accuracy as traditional methods.

NHC forecasters have already begun using DeepMind's AI model. Google says they're designed to support, not replace, human NHC forecasters. (Although President Trump's National Weather Service cuts have already reduced its headcount.) The company is also careful to repeatedly describe its models as "experimental."

Google claims that its models offer fewer trade-offs than physics-based predictions. The more accurate those methods are at forecasting a hurricane's path, the worse they are at predicting its intensity. (And vice versa.) The company says its experimental system offers "state-of-the-art" accuracy for both.

DeepMind backs that up with data from real-life storms over the last two years. On average, its five-day hurricane track prediction gets 87 miles closer to the storm's actual path than ENS, a widely used traditional model. Google's was comparable to a 3.5-day prediction model. In other words, it's like gaining an extra 1.5 days of warning with the same level of confidence. The company says such an improvement typically takes over a decade to achieve.

Sample scren from Google DeepMind's hurricane tracking website. Map showing hurricane paths.
Google

Alongside the NHC collab, Google is launching a new website that you can try. Now in a public preview, Weather Lab lets you see the AI storm predictions. It lets you view both live and historical predictions. You can even compare them to physics-based models to see how the AI version measures up.

It's important not to treat Weather Lab's experimental forecasts as official. But the website could come in handy if you live in Hurricane Alley. You can check it out now.

This article originally appeared on Engadget at https://www.engadget.com/ai/google-deepmind-is-sharing-its-ai-forecasts-with-the-national-weather-service-173506456.html?src=rss

Β©

Β© Google

A graphic showing a view from above of a hurricane. Data and paths are overlaid, symbolizing predictions.
Received before yesterday

Microsoft says its Aurora AI can accurately predict air quality, typhoons, and more

23 May 2025 at 17:00
One of Microsoft’s latest AI models can accurately predict air quality, hurricanes, typhoons, and other weather-related phenomena, the company claims. In a paper published in the journal Nature and an accompanying blog post this week, Microsoft detailed Aurora, which the tech giant says can forecast atmospheric events with greater precision and speed than traditional meteorological […]

Trump just made it much harder to track the nation’s worst weather disasters

8 May 2025 at 18:17

The Trump administration's steep staff cuts at the National Oceanic and Atmospheric Administration (NOAA) triggered shutdowns of several climate-related programs Thursday.

Perhaps most notably, the NOAA announced it would be shuttering the "billion-dollar weather and climate disasters" database for vague reasons. Since 1980, the database made it possible to track the growing costs of the nation's most devastating weather events, critically pooling various sources of private data that have long been less accessible to the public.

In that time, 403 weather and climate disasters in the US triggered more than $2.945 trillion in costs, and NOAA notes that's a conservative estimate. Considering that CNN noted the average number of disasters in the past five years jumped from nine annually to 24, shutting down the database could leave communities in the dark on costs of emerging threats. All the NOAA can likely say is to continue looking at the historic data to keep up with trends.

Read full article

Comments

Β© Bloomberg / Contributor | Bloomberg

❌