No physics? No problem. AI weather forecasting is already making huge strides.
沒有物理學？沒問題。AI 天氣預報已經取得了巨大的進展。

Much like the invigorating passage of a strong cold front, major changes are afoot in the weather forecasting community. And the end game is nothing short of revolutionary: an entirely new way to forecast weather based on artificial intelligence that can run on a desktop computer.
就像強冷鋒帶來令人振奮的變化一樣，氣象預報界也正在發生重大變化。最終目標是一場徹底的革命：一種完全基於人工智能的全新天氣預報方式，可以在台式電腦上運行。

Today's artificial intelligence systems require one resource more than any other to operate—data. For example, large language models such as ChatGPT voraciously consume data to improve answers to queries. The more and higher quality data, the better their training, and the sharper the results.
今天的人工智能系統比任何其他系統都需要一種資源來運作——數據。例如，像 ChatGPT 這樣的大語言模型會大量消耗數據來改進查詢的答案。數據越多、質量越高，它們的訓練就越好，結果也就越精確。

However, there is a finite limit to quality data, even on the Internet. These large language models have hoovered up so much data that they're being sued widely for copyright infringement. And as they're running out of data, the operators of these AI models are turning to ideas such as synthetic data to keep feeding the beast and produce ever more capable results for users.
然而，即使在互聯網上，優質數據也是有限的。這些大型語言模型已經吸收了如此多的數據，以至於它們正被廣泛起訴侵犯版權。隨著數據的耗盡，這些人工智能模型的運營商正轉向合成數據等想法，以繼續餵養這個“巨獸”，並為用戶產生更強大的結果。

If data is king, what about other applications for AI technology similar to large language models? Are there untapped pools of data? One of the most promising that has emerged in the last 18 months is weather forecasting, and recent advances have sent shockwaves through the field of meteorology.
如果數據為王，那麼人工智能技術的其他應用（類似於大型語言模型）又如何呢？是否存在尚未開發的數據庫？在過去 18 個月中出現的最有希望的領域之一是天氣預報，最近的進展給氣象學界帶來了衝擊波。

That's because there's a secret weapon: an extremely rich data set. The European Centre for Medium-Range Weather Forecasts, the premiere organization in the world for numerical weather prediction, maintains a set of data about atmospheric, land, and oceanic weather data for every day, at points around the world, every few hours, going back to 1940. The last 50 years of data, after the advent of global satellite coverage, is especially rich. This dataset is known as ERA5, and it is publicly available.
這是因為有一個秘密武器：一個極其豐富的數據集。歐洲中期天氣預報中心 (ECMWF) 是世界上首屈一指的數值天氣預報機構，它維護著一個關於大氣、陸地和海洋天氣數據的數據集，這些數據涵蓋了全球各地每天每隔幾個小時從 1940 年至今的數據。在全球衛星覆蓋出現之後的過去 50 年的數據尤其豐富。這個數據集被稱為 ERA5，它是公開可用的。

It was not created to fuel AI applications, but ERA5 has turned out to be incredibly useful for this purpose. Computer scientists only really got serious about using this data to train AI models to forecast the weather in 2022. Since then, the technology has made rapid strides. In some cases, the output of these models is already superior to global weather models that scientists have labored decades to design and build, and they require some of the most powerful supercomputers in the world to run.
它不是為人工智能應用而創建的，但 ERA5 已被證明對此非常有用。計算機科學家直到 2022 年才真正開始認真地使用這些數據來訓練人工智能模型來預測天氣。從那時起，這項技術取得了飛速的進步。在某些情況下，這些模型的輸出已經優於科學家們花費數十年時間設計和構建的全球天氣模型，而這些模型需要一些世界上最強大的超級計算機才能運行。

"It is clear that machine learning is a significant part of the future of weather forecasting," said Matthew Chantry, who leads AI forecasting efforts at the European weather center known as ECMWF, in an interview with Ars.
“很明顯，機器學習是天氣預報未來的一個重要組成部分，”領導歐洲天氣預報中心 (ECMWF) 人工智能預報工作的 Matthew Chantry 在接受 Ars 採訪時表示。

It’s moving fast 它正在快速發展

John Dean and Kai Marshland met as undergraduates at Stanford University in the late 2010s. Dean, an electrical engineer, interned at SpaceX during the summer of 2017. Marshland, a computer scientist, interned at the launch company the next summer. Both graduated in 2019 and were trying to figure out what to do with their lives.
John Dean 和 Kai Marshland 在 2010 年代後期於史丹佛大學就讀大學時相識。Dean 是一名電機工程師，在 2017 年夏天於 SpaceX 實習。Marshland 是一名電腦科學家，則於次年夏天在這家發射公司實習。兩人皆於 2019 年畢業，並正在思考未來的人生方向。

"We decided we wanted to solve the problem of weather uncertainty," Marshland said, so they co-founded a company called WindBorne Systems.
「我們決定要解決天氣的不確定性問題，」Marshland 表示，因此他們共同創立了一家名為 WindBorne Systems 的公司。

The premise of the company was simple: For about 85 percent of the Earth and its atmosphere, we have no good data about weather conditions there. A lack of quality data, which establishes initial conditions, represents a major handicap for global weather forecast models. The company's proposed solution was in its name—wind borne.
這家公司的理念很簡單：地球及其大氣層約有 85% 的區域缺乏良好的天氣狀況數據。缺乏建立初始條件的品質數據是全球天氣預報模型的一大障礙。該公司的解決方案就在其名稱中：wind borne（風載）。

Dean and Marshland set about designing small weather balloons they could release into the atmosphere and which would fly around the world for up to 40 days, relaying useful atmospheric data that could be packaged and sold to large, government-funded weather models.
Dean 和 Marshland 著手設計可以釋放到大氣中並環繞世界飛行長達 40 天的小型氣象氣球，這些氣球會傳回有用的氣象數據，這些數據可以打包出售給大型、政府資助的天氣模型。

Weather balloons provide invaluable data about atmospheric conditions—readings such as temperature, dewpoints, and pressures—that cannot be captured by surface observations or satellites. Such atmospheric "profiles" are helpful in setting the initial conditions models start with. The problem is that traditional weather balloons are cumbersome and only operate for a few hours. Because of this, the National Weather Service only launches them twice daily from about 100 locations in the United States.
氣象氣球提供了關於大氣條件的寶貴數據，例如溫度、露點和氣壓等讀數，這些數據是地面觀測或衛星無法捕捉到的。這些大氣「剖面」有助於設定模型開始使用的初始條件。問題是傳統的氣象氣球既笨重又只能運行幾個小時。因此，美國國家氣象局每天只在美國約 100 個地點釋放兩次氣象氣球。

Dean and Marshland developed much smaller balloons, each with a mass of less than 6 pounds and designed to persist in the atmosphere for weeks. By launching hundreds a day, over time, they can accrue data from around the world. WindBorne now operates the largest atmospheric balloon constellation in the world, Marshland said.
Dean 和 Marshland 開發了小得多的氣球，每個氣球的重量不到 6 磅，設計可在空中停留數週。Marshland 表示，通過每天發射數百個氣球，隨著時間的推移，他們可以積累來自世界各地的數據。WindBorne 現在運營著世界上最大的大氣氣球星座。

To test the assimilation of this balloon data into forecast models, WindBorne began to develop its own weather model about a year ago. It chose to experiment with AI forecasting because traditional models, based on complex computational physics, require an extraordinary amount of computing power.
為了測試將這些氣球數據同化到預報模型中，WindBorne 大約在一年前開始開發自己的天氣模型。它選擇試驗 AI 預測，因為基於複雜計算物理的傳統模型需要非常大的計算能力。

“When we started to develop AI forecasting, I didn’t think it would be a more accurate model," Dean said. "It was a way to save computing power. A single desktop computer with a high-powered GPU can run it. That is insane compared to the compute power used for global forecast models.”
“當我們開始開發 AI 預測時，我不認為它會是一個更準確的模型，”Dean 說。“這是一種節省計算能力的方法。一台配備高性能 GPU 的台式電腦就可以運行它。與用於全球預報模型的計算能力相比，這簡直太瘋狂了。”

Pretty soon, however, the company's AI weather model, WeatherMesh, was performing better than traditional, physics-based models on tasks such as hurricane forecasting.
然而，很快，該公司的 AI 天氣模型 WeatherMesh 在颶風預測等任務上的表現就優於傳統的基於物理的模型。

"It was mind-blowing how incredibly well it worked," Dean said.
“它的效果好得令人難以置信，”Dean 說。

WindBorne now offers two products to customers: balloon data and an impressively accurate deep-learning model.
WindBorne 現在為客戶提供兩種產品：氣球數據和一個非常準確的深度學習模型。

Origins of AI forecasting
AI 預測的起源

Some early academic work on using deep learning techniques for weather forecasting began about six years ago. This form of machine learning is based on neural networks, essentially connected nodes that are layered in a manner inspired by biological brains. By ingesting data, neural networks can be "trained" to identify and classify information and recognize patterns and possibilities.
大約六年前，一些關於將深度學習技術用於天氣預報的早期學術工作開始了。這種機器學習形式基於神經網絡，本質上是相互連接的節點，其分層方式受到生物大腦的啟發。通過攝取數據，神經網絡可以被“訓練”來識別和分類信息，並識別模式和可能性。

Computer scientists were not overly optimistic that this approach would work because it was so wildly different from the science of weather forecasting that had been developed over decades. Traditional modeling uses complex physical equations to simulate the fluidic motion of the atmosphere. The most powerful global models take a set of initial weather conditions and then crunch through these equations to provide point forecasts for a grid a few miles across, out to 16 days, around the world.
計算機科學家對這種方法是否有效並不十分樂觀，因為它與幾十年來發展起來的天氣預報科學截然不同。傳統的建模使用複雜的物理方程式來模擬大氣的流體運動。最強大的全球模型採用一組初始天氣條件，然後通過這些方程式進行計算，為全球範圍內相隔幾英里的網格提供長達 16 天的點預報。

The ECMWF model is the best physics-based model in the world, although other countries, including the United States, Canada, and Japan, also run global weather models for various forecasting purposes.
ECMWF 模型是世界上最好的基於物理的模型，儘管其他國家，包括美國、加拿大和日本，也運行全球天氣模型用於各種預報目的。

The initial skepticism about AI models was eased in 2022. A physicist and data scientist named Ryan Keisler presented some promising initial returns with what he called "graph neural networks." Shortly afterward, scientists from the China-based Huawei multinational company released information about their efforts to develop the "Pangu-Weather" model. These initial results, later published in Nature, found that under certain circumstances, the Chinese deep-learning model outperformed even the physics-based ECMWF model.
2022 年，人們對 AI 模型的最初懷疑有所緩解。一位名叫 Ryan Keisler 的物理學家兼數據科學家用他所謂的“圖神經網絡”展示了一些有希望的初步成果。不久之後，來自中國的跨國公司華為的科學家發布了他們開發“盤古-天氣”模型的努力信息。這些初步結果後來發表在《自然》雜誌上，發現中國的深度學習模型在某些情況下甚至優於基於物理的 ECMWF 模型。

This sent a shockwave through the small community of scientists working with deep learning techniques and weather modeling. Chantry and the European weather center were among those paying attention as other models, such as Google's GraphCast, were released with similar promise. In early 2023, Chantry and a few colleagues began to study the possibilities, and in the summer of 2023, the member nations that fund the center agreed to support the development of a model.
這讓這個從事深度學習技術和天氣建模的小型科學家群體感到震驚。隨著其他模型（例如 Google 的 GraphCast）的發布並具有類似的希望，Chantry 和歐洲天氣中心也開始關注這些模型。2023 年初，Chantry 和幾位同事開始研究這種可能性，2023 年夏天，為該中心提供資金的成員國同意支持開發一個模型。

The AI-focused team remained small compared to the developers who worked on the physics-based model, partly because this approach required fewer resources. Radically fewer, in fact. WindBorne, which developed the WeatherMesh model, is a company of about two dozen people. Its model can run on a single, powerful desktop computer.
與基於物理的模型的開發人員相比，專注於 AI 的團隊仍然很小，部分原因是這種方法需要的資源更少。事實上，少得多。開發 WeatherMesh 模型的 WindBorne 是一家擁有約 24 名員工的公司。它的模型可以在一台功能強大的台式計算機上運行。

The European scientists set to work making an operational model based on the work of the other deep learning models. It didn't take long. By the end of last year, the new Artificial Intelligence/Integrated Forecasting System, or AIFS, was already producing "very promising" results. This spring, the European forecasters started to publish real-time forecasts. As a meteorologist working in the field today, I use them and find them to be an increasingly useful tool.
歐洲科學家開始著手基於其他深度學習模型的工作來製作一個可操作的模型。沒過多久。到去年年底，新的人工智能/綜合預報系統（AIFS）已經產生了“非常有希望”的結果。今年春天，歐洲預報員開始發布實時預報。作為一名今天在該領域工作的氣象學家，我使用它們並發現它們是一個越來越有用的工具。

But as someone who is not particularly literate in artificial intelligence technology, I was eager to find out how they worked. If I'm going to rely on this tool, I'd like to understand what I'm using.
但是作為一個對人工智能技術不是特別了解的人，我渴望了解它們是如何工作的。如果我要依賴這個工具，我想了解我正在使用的東西。

How they work 它們如何運作

The first thing to understand about a deep-learning forecast model is that it uses no physics-based modeling of the atmosphere at all. It is also not a large language model. “It is not like asking Chat GPT to predict the weather," Chantry said.
要了解深度學習預測模型，首先要明白它完全沒有使用任何基於物理的大氣建模。它也不是大型語言模型。Chantry 表示：「這不像是在要求 Chat GPT 預測天氣。」

Essentially, a deep-learning model works by learning. A snapshot of the Earth and its weather conditions is shown to the model—values like temperature, pressure, humidity, winds, and much more at various levels of the atmosphere. Then the model is shown what conditions were like six hours later around the Earth. The model then "learns" this relationship between weather now and conditions a few hours later.
從本質上講，深度學習模型是通過學習來運作的。模型會顯示地球及其天氣狀況的快照，包括不同大氣層級的溫度、壓力、濕度、風速等數值。然後，模型會顯示六小時後全球的狀況。然後，模型會「學習」現在的天氣狀況與數小時後的狀況之間的關係。

The process is repeated many times over. This is where the ERA5 data is incredibly valuable. It has nearly six decades of high-quality data for every day, every few hours, and for points all around the world. By ingesting all this data, the model gets better and better at recognizing patterns and making connections about conditions now—say, a large, low-pressure system over the Northern Atlantic Ocean—and what that means for weather downstream over Europe and Asia over the coming week to 10 days.
這個過程會重複很多次。這就是 ERA5 數據的價值所在。它擁有近 60 年的高品質數據，涵蓋全球各地每一天、每隔幾個小時的數據。通過吸收所有這些數據，模型在識別模式和建立當前狀況（例如北大西洋上空的大型低壓系統）與未來一到十天歐洲和亞洲的天氣狀況之間的關聯方面變得越來越出色。

One of the initial concerns about this approach was whether there was enough data in ERA5 to make robust forecasts. But given the improving performance of the models, it appears there is indeed enough information.
對這種方法的最初擔憂之一是 ERA5 中是否有足夠的數據來進行可靠的預測。但鑑於模型性能的提高，看來確實有足夠的信息。

Part of the challenge for Chantry and his colleagues is identifying what works well with the AIFS model and what needs improvement. For example, deep learning weather models have proven to be excellent at forecasting the tracks of hurricanes. But while these models are better at predicting where hurricanes will go, they tend to be lower-performing on the intensity changes of such storms relative to physics-based models.
Chantry 和他的同事面臨的挑戰之一是確定哪些方法對 AIFS 模型有效，哪些方面需要改進。例如，深度學習天氣模型已被證明非常擅長預測颶風的軌跡。但是，儘管這些模型更擅長預測颶風的行進路線，但與基於物理的模型相比，它們在預測此類風暴的強度變化方面的表現往往較差。

For now, physics-based weather models aren't going anywhere. They're incredibly powerful tools that have significantly improved our ability to make five-, seven- and occasionally even 10-day weather forecasts for major events. They're trusted by forecasters around the world. But what does the future look like?
目前，基於物理的天氣模型不會消失。它們是非常強大的工具，顯著提高了我們對重大事件進行 5 天、7 天，有時甚至 10 天天氣預報的能力。它們得到了全球預報員的信任。但未來會是什麼樣子？

The first step is potentially changing the way data is assimilated into AI-based models. At present, they almost universally use a set of initial conditions produced by a physics model. That is, a model like the ECMWF spends an enormous amount of computing power to collect data from buoys, surface stations, weather balloons, airplanes, ships, satellites, and many other sources and then synthesizes a set of initial conditions for grid points across the planet. All models then take this as the beginning "state" of the planet's weather and forecast from that.
第一步可能是改變將數據同化到基於 AI 的模型中的方式。目前，它們幾乎普遍使用由物理模型生成的一組初始條件。也就是說，像 ECMWF 這樣的模型會花費大量的計算能力來收集來自浮標、地面站、氣象氣球、飛機、船舶、衛星和許多其他來源的數據，然後合成一組全球網格點的初始條件。然後，所有模型都將其作為地球天氣的初始「狀態」，並以此為基礎進行預測。

However, Chantry and others are working on techniques for AI models to ingest current observations and thereby perform both the data assimilation and forecasting parts of weather modeling. This, he says, is actually a harder problem than training AI models.
然而，Chantry 和其他人正在研究讓 AI 模型吸收當前觀測結果的技術，從而執行天氣建模中的數據同化和預測部分。他說，這實際上是一個比訓練 AI 模型更難的問題。

"That version is the completely revolutionary version," he said. "It’s a fascinating research topic that flips the table over." 
「那個版本是完全革命性的版本，」他說。「這是一個引人入勝的研究課題，它顛覆了傳統。」

Something like that may be possible a decade from now.
類似的事情可能在十年後成為可能。

What all this means
這一切意味著什麼

I started writing about the weather about 20 years ago, and the modeling tools we had back then were fairly simple. You had a few different kinds of models, and they were generally not very good. With major hurricanes like Katrina, there was a ton of uncertainty about where they would go. At the time, the average positional error in a five-day forecast was about 425 miles, about the distance from New York City to Bangor, Maine.
我大約在 20 年前開始撰寫有關天氣的文章，當時我們使用的建模工具相當簡單。當時只有幾種不同的模型，而且它們通常不是很好用。對於像卡特里娜這樣的重大颶風，它們的移動路徑存在著很大的不確定性。當時，五天預報的平均位置誤差約為 425 英里，大約是從紐約市到緬因州班戈的距離。

Today, that error is fewer than 200 miles. It's far from perfect, but it's a huge difference. Further improvements would help narrow down evacuation areas, saving an incredible amount of time, money, and heartache.
今天，這個誤差已經減少到不到 200 英里。雖然還遠未達到完美，但已經是一個巨大的差異。進一步的改進將有助於縮小疏散區域，從而節省大量的時間、金錢和痛苦。

The Atlantic hurricane season officially began on June 1, and it's expected to be a rather busy one. A good forecaster looks at many different models and understands that for any particular storm, one model may handle the atmospheric setup better than others. As we get into the season, I'm looking at Chantry's AIFS model as one of those tools and will evaluate its performance.
大西洋颶風季於 6 月 1 日正式開始，預計今年將會是一個相當活躍的颶風季。一個好的預報員會查看許多不同的模型，並且了解對於任何特定的風暴，一個模型可能會比其他模型更好地處理大氣環境。隨著颶風季的到來，我將 Chantry 的 AIFS 模型視為其中一種工具，並將評估其性能。

However, such AI models have not entirely entered the mainstream. Some of the best forecasters in the world work for the National Hurricane Center in Miami. This is the office within NOAA that is charged with forecasting hurricanes and issuing warnings for the entire Atlantic basin, including the United States. Having observed their work closely for a quarter of a century, they're fantastic.
然而，這樣的 AI 模型尚未完全進入主流。一些世界上最優秀的預報員在邁阿密的國家颶風中心工作。這是 NOAA 內負責預測颶風並向整個大西洋盆地（包括美國）發布警報的辦公室。近距離觀察他們的工作 25 年後，我發現他們非常出色。

This year, forecasters at the center will not be using the AI models for operational forecasts, a source told Ars. These are the official forecasts that include the familiar "cone of uncertainty" and warning areas. However, forecasters will be evaluating the new tools.
據一位消息人士告訴 Ars，今年該中心的預報員不會將 AI 模型用於業務預報。這些是官方預報，包括熟悉的“不確定性錐體”和警報區域。然而，預報員將會評估這些新工具。

This is the first Atlantic hurricane season in which many of these new models will be fully available in real time. It's one thing to perform well on tests or in a "hindcast," where a model is tested on past operational data. It's another to make actionable predictions.
這是第一個大西洋颶風季，在這個颶風季中，許多新的模型將可以完全實時地使用。在一項測試中或在「後報」（模型在過去的運行數據上進行測試）中表現良好是一回事。而做出可操作的預測是另一回事。

So in the coming months, on one of the biggest stages imaginable—a blockbuster Atlantic hurricane season where storms may threaten some of the largest cities in the United States—models such as AIFS, WeatherMesh, and others will have a chance to strut their stuff in real time.
因此，在接下來的幾個月中，在一個可以想像到的最大舞臺上——一個可能威脅美國一些最大城市的重磅大西洋颶風季——像 AIFS、WeatherMesh 和其他模型這樣的模型將有機會實時展示其實力。

We'll be watching closely.
我們將密切關注。