Earthmover 和 Hugging Face 着手解决快速天气 AI 的慢速环节

该教程将 Microsoft 的 Aurora 与 Earthmover 的数据和 Hugging Face 的计算资源配对，把一个 1GB 的数据获取问题变成了可运行的预测。

By · Published

Primary source: Hugging Face Newsroom

为何重要

开放的天气模型越来越容易获取，这将工程负担转向数据访问和验证。Earthmover 正在将其阵列基础设施定位为每次模型运行仍然需要的那一层。

A dynamic holographic weather map shows rapidly updating forecasts, with luminous streams of data converging and being processed by advanced computing.

Ryan Abernathey (@rabernat) and Joe Hamman, the climate scientists who founded Earthmover, published a workflow with Hugging Face on September 8th that makes open-weight AI weather models easier to initialize, run and evaluate.…

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.