<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>气候科技 on AI 早报</title><link>https://ai-news.example.com/categories/%E6%B0%94%E5%80%99%E7%A7%91%E6%8A%80/</link><description>Recent content in 气候科技 on AI 早报</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Tue, 07 Jul 2026 23:13:01 +0800</lastBuildDate><atom:link href="https://ai-news.example.com/categories/%E6%B0%94%E5%80%99%E7%A7%91%E6%8A%80/feed.xml" rel="self" type="application/rss+xml"/><item><title>[EN] 谷歌推出生成式AI模型SEEDS，低成本量化天气预报不确定性</title><link>https://ai-news.example.com/articles/en-aiseeds/</link><pubDate>Tue, 07 Jul 2026 23:13:01 +0800</pubDate><guid>https://ai-news.example.com/articles/en-aiseeds/</guid><description>谷歌发布基于扩散概率模型的SEEDS（可扩展集合包络扩散采样器），能以极低成本生成大规模天气预报集合，有效量化极端天气的不确定性。</description></item><item><title>[EN] 生成式AI量化天气预报不确定性：谷歌推出SEEDS模型</title><link>https://ai-news.example.com/articles/en-aiseeds/</link><pubDate>Sun, 05 Jul 2026 01:51:59 +0800</pubDate><guid>https://ai-news.example.com/articles/en-aiseeds/</guid><description>谷歌发布基于扩散概率模型的生成式AI框架SEEDS，能以极低计算成本大规模生成天气预报集合，弥补传统物理模型在高分辨率、大集合生成上的不足，提升对极端天气事件的概率判断。</description></item></channel></rss>