跳到正文
HNHacker News·

WeatherNext 3

AI 摘要

WeatherNext 3 是 DeepMind 最先进的全球天气 AI 模型,能够每小时生成预报。该模型为谷歌产品(如搜索、地图和 Gemini)提供本地天气数据,帮助个人和企业做出更明智的决策。值得一提的是,WeatherNext 3 曾协助国家飓风中心更准确地预测了飓风 Melissa 在牙买加的历史性登陆。

时间与来源
发布
09/03 16:06 UTC+0
收录
09/08 00:00 UTC+0
来源类型
官方发布
档位
社区
信源状态
正常

档位是按信源手工设定的编辑判断,不是逐条打分。

爆款判定
判定依据
热度约为该来源近期上榜条目中位水平的 3.8 倍
触发条目
WeatherNext 3
指标对比
199 vs 中位 52(20 条基线样本)
检出时间
09/07 22:00
正文 · 官方 API

Our most advanced global weather AI model yet

WeatherNext 3 is the first global weather model that generates forecasts every hour of the day. It delivers local data for people and enterprises, into Google products like Search, Maps, and Gemini, so we can all make smarter, better-informed decisions.

- Overview

- Capabilities

- Impact

- Try WeatherNext 3

Smarter forecasting. Smarter decisions.

Every day, the weather influences billions of decisions. Some are as simple as grabbing an umbrella. Others shape entire economies. As our weather grows more extreme, the stakes grow higher.

For decades, weather forecasting worked on numerical predictions and physical approximations. These models were a triumph of science and engineering – but also complex and costly to operate.

With WeatherNext 3, forecasters get better reach, speed, and detail than ever before. Every hour of the day, every day of the year. So that we can all – from individuals to enterprises – make smarter, better-informed decisions.

Hourly forecasts

Unlike previous models, WeatherNext 3 draws directly from raw satellite imagery. This enables the model to generate forecasts every hour, helping users track fast-changing weather conditions like rain and snow.

Increased resolution

WeatherNext 3 can predict all surface variables – including weather station targeted temperature and humidity at 5km resolution, and other surface variables like wind at 10km. This results in significantly more accurate forecasts – even in locations the model hasn’t encountered in training.

Industry application

WeatherNext 3 is designed for industry application, forecasting relevant variables like renewable energy. For wind and solar farms, WeatherNext 3 covers variables like radiation and cloud cover, helping operators to manage more efficiently.

How WeatherNext helped the National Hurricane Center better predict Hurricane Melissa’s historic landfall in Jamaica

来源·Hacker News·deepmind.google·官方 API