小道消息:
据说,2025年ECMWF会全部免费开放
IFS高分辨率数值模式预报数据,AIFS的到来是不是提前铺垫呢?有AI加持是否再次表明ECMWF预报能力遥遥领先呢?若头部玩家真要掀桌子,那可真是造福全人类啊!(非官方消息,待验证!)
(https://charts.ecmwf.int/?facets=%7B%22Product%20type%22%3A%5B%22Experimental%3A%20AIFS%22%5D%7D)
ECMWF
:
推出新集合预报模型AIFS
(领略气象)
近日,
ECMWF
推出
IFS
(
综合预报系统的新伙伴——人工智能综合预报系统)
AIFS
(
Artificial
Intelligence/Integrated
Forecasting
System
)。
AIFS
是
ECMWF
于
2023
年夏季开展的新机器学习项目的三个组成部分之一,该项目旨在将机器学习应用扩展到地球系统建模。
AIFS
同时具备人工智能与综合预报能力,目前已进入其
alpha
版本。
AIFS
alpha
版本有
13
个压力级别,在约
1
度的分辨率下运行,并对风、温度、湿度和位势进行预测。
AIFS
可以预测地面上
2
米的温度,
10
米的风,地面压力等。
ECMWF
将定期更新以提高分辨率,并添加降水等字段。该
alpha
版本使用图神经网络(
Graph
Neural
Networks
)与高斯网格,并被训练成使用最小均方误差的确定性模型。
AIFS
的到来标志着
ECMWF
在机器学习领域的进步。下一步,
ECMWF
将计划开发一个新的集成系统。
ECMWF unveils alpha version of new ML model
ECMWF is today launching a newborn companion to the IFS (Integrated Forecasting System), the AIFS, our Artificial Intelligence/Integrated Forecasting System (one “I" covering both Intelligence and Integrated).
ECMWF今天推出了IFS(综合预报系统)的新生伴侣--AIFS,即我们的人工智能/综合预报系统(一个 "I "涵盖智能和综合)。
The AIFS is barely a few months old and proudly entering its alpha version. Its arrival signals the strengthening of ECMWF’s efforts in the field of machine learning (ML), which we have been navigating for a few years now.
AIFS 刚刚诞生几个月,并自豪地进入了阿尔法版本。它的到来标志着ECMWF在机器学习(ML)领域的努力得到了加强。
The AIFS forms one of three components of our new ML project, which began in summer 2023 and aims to expand our applications of machine learning to Earth system modelling.
AIFS是我们新ML项目的三个组成部分之一,该项目于2023年夏季启动,旨在将机器学习应用于地球系统建模。
As our AIFS debuts today with its first outing onto our website, you will be able to view its promising results for yourself and follow our ongoing development. We are scoring it against our long-standing IFS, and you will also be able to check it against the other AI-based models that we are making available on our website on a daily basis.
今天,我们的 AIFS 首次在我们的网站上亮相,您将能够亲眼目睹其可喜的成果,并关注我们的持续发展。我们正在将它与我们长期使用的 IFS 进行比较,您也可以将它与我们每天在网站上提供的其他基于人工智能的模型进行比较。
Physics-based numerical weather prediction models, for us the IFS, are still key in all of this. The IFS is unparalleled by ML models for the breadth of variables it predicts and its spatial resolution.
对我们来说,基于物理学的数值天气预报模型,即 IFS,仍然是所有这些模型中的关键。IFS 在预测变量的广度和空间分辨率方面都是 ML 模式无法比拟的。
IFS data assimilation provides the live initial conditions and creates training datasets. ECMWF remains firmly committed to further improvement of the IFS.
IFS 数据同化提供了实时初始条件,并创建了训练数据集。ECMWF将继续致力于进一步改进IFS。
Our AIFS team explains the choice of technology the system was built on, the resolution of this alpha version, which fields it makes predictions for, and how it compares with the IFS:
我们的AIFS团队解释了该系统的技术选择、该alpha版本的分辨率、它对哪些领域进行预测,以及它与IFS的比较:
What is the AIFS?
什么是 AIFS?
In thinking about what technology to build on we considered all the interesting architectures recent papers have developed. Do we want to leverage our knowledge of spectral transforms and build something like NVIDIA’s Neural Operator system, FourCastNet? Do we want to leverage the vast research that goes into vision transformers and build something like Pangu-Weather, FengWu or FuXi? Or do we want to utilise the grid-flexibility and parameter efficiency of Graph Neural Networks like the work of Ryan Keisler or Google Deepmind’s GraphCast?
在考虑以什么技术为基础时,我们考虑了近期论文中提出的所有有趣的架构。我们是否想利用我们在光谱变换方面的知识,构建类似英伟达的神经运算器系统 FourCastNet?我们是想利用视觉变换器的大量研究成果,构建类似盘古气象、风物或伏羲的系统?还是利用图形神经网络的网格灵活性和参数效率,如 Ryan Keisler 或 Google Deepmind 的 GraphCast?
For this alpha version we have chosen Graph Neural Networks. But we’ve been keen to build a flexible code base so that we can replace any piece of the system if new external or internal developments show promise.
在这个 alpha 版本中,我们选择了图神经网络。但我们一直热衷于建立一个灵活的代码库,以便在外部或内部的新发展显示出前景时,我们可以替换系统的任何部分。
Across many aspects, including what data we train on, and how we train the AIFS, we have taken inspiration from all of the previous works referenced above.
在许多方面,包括我们训练的数据以及训练 AIFS 的方式,我们都从上述所有前人的工作中汲取了灵感。
Graph Neural Networks allow us to move away from lat-lon grids, which have many points near the poles, and use reduced Gaussian grids which have near equal distance between grid-points no matter where you are on the globe.
图神经网络让我们摆脱了两极附近有很多点的纬线网格,而使用了缩小的高斯网格,无论你在地球上的哪个位置,网格点之间的距离几乎相等。
These are also the grids which are used by the IFS to create ERA5 and operational initial conditions.
这些网格也是 IFS 用来创建 ERA5 和运行初始条件的网格。
This alpha AIFS version has 13 pressure levels, runs at approximately 1 degree resolution and makes predictions for wind, temperature, humidity and geopotential. At the surface AIFS makes predictions for 2 m temperature, 10 m winds, surface pressure and more. We’ll be regularly updating this to increase resolution, and add fields like precipitation.
这个阿尔法 AIFS 版本有 13 个气压等级,运行分辨率约为 1 度,可预测风、温度、湿度和位势。在地表,AIFS 可预测 2 米气温、10 米风速、地表气压等。我们将定期更新,以提高分辨率,并增加降水等领域。
AIFS was trained to minimise mean squared error, meaning it’s been trained to use as a deterministic model. One of our big next steps, and something we’ll be talking more about in the future, will be around developing an ensemble system.
AIFS 的训练目标是最小化均方误差,这意味着它已被训练成一个确定性模型。我们下一步要做的一件大事,也是我们将来会更多讨论的事情,就是开发一个集合系统。
The IFS’s primary offering now is an ensemble prediction system because we know this is the most useful way of making medium-range forecasts.
IFS现在主要提供的是集合预测系统,因为我们知道这是进行中期预测最有用的方法。
Here's how we compare with the IFS, for geopotential height at 500 hPa. In meteorology, this is the go-to first measure of extra-tropical large-scale flow, but it is still only a single measure of a forecasting model.
以下是我们与 IFS 在 500 hPa 的位势高度方面的比较。在气象学中,这是衡量热带外大尺度气流的首选指标,但它仍然只是预报模式的单一指标。
More plots can be found on the charts page, which will be expanded as we go. We see that our coarse model is already proving very promising on this metric, which is consistent with results from other ML models.
更多图表可在图表页面上找到,我们将不断扩大该页面。我们可以看到,我们的粗模型在这一指标上已经证明非常有前途,这与其他 ML 模型的结果是一致的。
Root-mean-square error in geopotential height at 500 hPa for the IFS and the AIFS in the months of June–July–August 2023 in the northern hemisphere extratropics.
2023 年 6-7-8 月北半球外热带地区 IFS 和 AIFS 500 百帕高度的均方根误差。
We’ll be writing more in the coming days and weeks, going into more detail on the things that are and aren’t working. We hope you’ll stick around for the journey we are taking…
在接下来的几天和几周里,我们将撰写更多文章,更详细地介绍行之有效和行不通的方法。希望您能继续关注我们的旅程...
来源:
领略气象、ECMWF官网(openai翻译)
声明:
欢迎转载、转发本号原创内容,可留言区留言或者后台联系小编(微信:gavin7576)进行授权。气象学家公众号转载信息旨在传播交流,其内容由作者负责,不代表本号观点。文中部分图片来源于网络,如涉及作品内容、版权和其他问题,请后台联系小编处理。