Recently The New York Times reported the following:
Google Introduces A.I. Agent That Aces 15-Day Weather
Forecasts (2/2)
GenCast, from the company’s DeepMind division,
outperformed the world’s best predictions of deadly storms as well as everyday weather.
By William J. Broad
Dec. 4, 2024
(continue)
Dr. Lam of DeepMind noted that GenCast’s generative skills
were rooted in factual data gathered from nature rather than the internet,
notorious for its confusing mix of facts, biases and fallacies. “We have a
ground truth,” he said of its dependence on natural phenomena. “We have a
reality check.”
The new agent’s forecasts are probabilistic — like those on the weather apps of smartphones. For instance, GenCast can give a range of percentages for the likelihood of rain in a specific region on a given day.
In contrast, its DeepMind predecessor, GraphCast, offers a single forecast for a particular time and location. Known as deterministic, its method is essentially a best guess that gives no indication of the prediction’s uncertainty.
Despite all the effort that goes into those calculations, Dr. Price of DeepMind said, the new agent can generate a 15-day forecast in minutes compared with hours for a supercomputer. That can make its projections much timelier — an advantage in tracking fast-moving storms.
GenCast, the team says, can predict with great accuracy the paths of hurricanes, which annually can take thousands of lives and rack up hundreds of billions of dollars in property damage. The Nature paper said comparative testing showed that its hurricane track predictions consistently outdid those of the European center.
Dr. Price, the paper’s lead author, concurred. He said the problem lay in training data limitations on hurricane wind speed. The weather team, he added, was confident it could devise a solution.
“The status quo isn’t going to disappear,” Dr. Emanuel said. “Perhaps the two of them working together will prove to be the best way forward.”
For its part, the DeepMind team acknowledged its heavy reliance on the conventional world of weather readings — noting, for instance, how its A.I. training data comes from the giant European weather archive. Its computations also start with a snapshot of the world’s current weather, what the team calls initial conditions.
The team hopes that other weather experts will test its new technology. Dr. Price said that the DeepMind team would share online its A.I. agent and underlying computer code.
He added that GenCast’s weather predictions would soon be posted publicly on Google’s Earth Engine and Big Query, giving scientists access to the new forecasts.
“We’re excited for the community to use and build on our research,” Dr. Price said.
Dr. Chantry of the European center said Google and DeepMind might have hidden their A.I. advance behind a wall of corporate secrecy, using it “to make a better weather forecast for their own apps and telling no one how they did it.”
Instead, he added, the emerging field has embraced a public openness that’s helping “lots and lots of people engage in this revolution.
Translation
谷歌推出人工智能體可顯著做好15 日天氣預報 (2/2)
該公司
DeepMind 部門的
GenCast 的表現優於世界上對致命風暴和日常天氣的最佳預測。
(繼續)
DeepMind 的
Lam 博士指出,GenCast
的生成技能植根於從大自然而不是互聯網收集的實數,眾人皆知互聯網是由實數、偏見和謬誤的撲朔迷離混合而成。談到它對自然現象的依賴時他說道: 「我們有地面上的實况」; 「我們進行了實質檢驗」。
新人工智能體的預測是機率性的, 就像智慧型手機天氣應用程式上的預測一樣。例如,GenCast 可以給出特定日期特定地區下雨可能性的百分比範圍。
相較之下,其 DeepMind 的前身 GraphCast 提供針對特定時間和地點的單一預測。其方法被稱為確定性方法,本質上是一種最佳猜測,不會顯示預測的不確定性。
機率預測被認為比確定性預測更加細緻和複雜,並且更難創建。通常,GenCast 預測會從一組 50 個或更多的預測中提取其機率範圍。
DeepMind 的 Price 博士表示,已在這些計算中付出了很多努力,新人工智能體可以在幾分鐘內產生 15 天的預測,相比超級電腦需要幾個小時。這可以使其預測更加及時 - 這在追蹤快速移動的風暴方面是一個優勢。
團隊表示,GenCast 可以非常準確地預測颶風的路徑,颶風每年都會奪走數千人的生命,並造成數千億美元的財產損失。 《自然》雜誌的論文稱,比較測試表明,其颶風路徑預測始終優於歐洲中心的預測。
麻省理工學院的Emanuel博士表示 DeepMind 團隊沒有提及其新人工智能體只提供很少有關颶風強度的資訊。
論文的主要作者Price博士對此表示同意。他說,問題在於颶風風速的訓練資料限制。他補充說,氣象團隊有信心找到解決方案。
Emanuel 博士認為,GenCast 很可能會補充而不是取代目前的方法。他說,各類型在預測構成天氣的各種紛亂變化現象方面都有自己的優點和缺點。
Emanuel博士說: 「現有的局面不會消失」。 「也許雙方合作將被證明是向前進步的最佳方法」。
就 DeepMind 團隊而言,它承認自己嚴重依賴傳統的天氣讀數 - 例如,人工智能的訓練資料是如何來自龐大的歐洲天氣檔案。它的計算也是從世界目前天氣的簡介開始,該團隊稱之為開啟狀況。
該團隊希望其他氣象專家能夠測試其新技術。 Price 博士表示,DeepMind 團隊將在網路上分享其 人工智能體和其底層電腦代碼。
他補充說,GenCast 的天氣預報很快就會在Google的 Earth Engine 和 Big Query 上公開發佈,讓科學家能夠獲得新的預報。
Price博士說: 「我們很高興本群體能夠使用和發展我們的研究」。
歐洲中心的Chantry博士表示,谷歌和 DeepMind 可能隱藏了他們的人工智能的進展於其公司保密牆後面,利用它 “把自己的應用程式做出更好的天氣預報,及不告訴任何人他們是如何做到的。”
反而,他補充說,這個新興領域已經接受了公眾開放,它正在幫助「很多人參與這場變革」。
So, we all know that since the 1960s,
the chaotic nature of Earth’s atmosphere would put a limit on how far into the
future forecasts may be. Since the early 2000s, the great difficulty of this task keeps
reliable forecasts restricted to about a week. Now a new artificial
intelligence tool has broken the barriers and achieved 15-day weather
forecasts. It outperforms the world’s best forecasts in speed in tracking
deadly storms. This new agent can generate a 15-day forecast in
minutes compared with hours for a supercomputer. As its projections are much
timelier, it has an advantage in tracking fast-moving storms. This is good news
to everyone in the field of weather forecasting.