AI 预报飓风提前一周锁定五级，靠的是统计不是物理

核心论点 · 点时间戳可跳到原声

原话 · 已逐字校验

we started to see the model becoming quite confident that it was going to turn into a category 5 hurricane, which is the strongest category of hurricane.

我们开始看到模型相当有信心地认为，它会变成五级飓风，也就是最强级别的飓风。

Peter Battaglia2:10

this was the lowest intensity storm that the National Hurricane center had ever forecast to become category 5. They they had never made a category 5 forecast from such a low intensity.

这是国家飓风中心有史以来预报会变成五级飓风的强度最低的风暴。他们从来没有从这么低的强度做出过五级预报。

Peter Battaglia5:10

we can't observe every butterfly. So there's a fundamental limit to what we can observe and that then translates to a fundamental limit in what we can predict.

我们没法观测每一只蝴蝶。所以我们的观测能力存在一个根本极限，这个极限又转化成我们预报能力的根本极限。

Peter Battaglia12:11

if they're spaghetti plots and they're all over the place then the model is saying it's very difficult for us to understand what could happen and that's a very important thing because it's a fact of how we forecast weather. We cannot know certain things.

如果那些意大利面图到处都是，那模型就是在说：我们很难理解会发生什么。这非常重要，因为这就是天气预报的本质——有些事我们就是无法知道。

Peter Battaglia25:17

With AI models, their failure mode tends to be when they start to make errors, they tend to more just predict average weather. Like predicting the average weather is actually a pretty good way to predict weather. And it's actually the oldest way to predict weather.

AI 模型的失败模式是：当它们开始出错时，往往只是去预测平均天气。而预测平均天气其实是相当不错的预报方式，实际上也是最古老的预报方式。

Peter Battaglia36:22

while the model might not have seen this specific instance of this storm at this location and this trajectory, it has seen intense weather in other parts of the globe

模型也许没见过这场风暴在这个位置、这条路径上的这个具体实例，但它在全球其他地方见过强天气。

Peter Battaglia37:22

most weather observations are actually not even used by weather agencies. So, there's I actually think there's a ton of data. There's a ton of problems that haven't even been touched yet.

大多数气象观测其实根本没被气象机构使用。所以我真的认为有海量数据，有海量问题根本还没被碰过。

Peter Battaglia39:22

I think we will move away from approximating the solutions to equations, but we're not moving away from physics. The data was also created by physics.

我认为我们会离开「近似求解方程」这条路，但我们不会离开物理。数据本身也是物理造出来的。

Peter Battaglia40:23

数字与实体

术语

numerical weather prediction数值天气预报

用超级计算机近似求解流体运动方程、逐步外推的经典预报方法。

GraphCastGraphCast

DeepMind 早期全球 AI 天气模型，一次预测全球 10 天天气。

GenCastGenCast

DeepMind 的概率天气模型，预测多种可能情景而非单一平均天气。

functional generative networks函数生成网络

DeepMind 自研的概率预报技术，通过微调网络权重生成多样情景。

spaghetti plots意大利面图

把多个概率情景的路径画在一起，散得越开表示不确定性越大。

load forecasting负荷预测

预测电网的电力需求，主要受温度驱动。

收听指南