Your current location:HOME >world >Scientists develop new AI model for weather forecasting 正文
TIME:2024-05-08 23:37:17 Source: Internet compilationEdit:world
(Xinhua) 14:29, December 11, 2023SHANGHAI, Dec. 10 (Xinhua) -- Scientists have developed a new model
SHANGHAI, Dec. 10 (Xinhua) -- Scientists have developed a new model for sub-seasonal forecasts using artificial intelligence (AI) technology.
The new model, "FuXi-Subseasonal," developed by scientists from the Shanghai Academy of Artificial Intelligence for Science, Fudan University, and China's National Climate Center, represents a significant advancement in AI climate modeling by extending the forecasting range to 42 days.
The new model was unveiled Friday at the China Pavilion during the ongoing 28th session of the Conference of the Parties to the United Nations Framework Convention on Climate Change (COP28) in Dubai, United Arab Emirates, according to Fudan University.
According to scientists, sub-seasonal anomalies significantly contribute to high-impact climate events, so improving prediction skills at this timescale is a pressing requirement for advancing climate science.
The new model integrates the transformer architecture with guided random samples in a latent space to account for underlying uncertainty in sub-seasonal forecasts. By doing so, the model can generate forecasts with accuracy superior to those of the European Centre for Medium-Range Weather Forecasts (ECMWF), said Qi Yuan, director of the Shanghai Academy of Artificial Intelligence for Science and a professor of Fudan University.
The new model has overcome challenges related to inaccurate initial conditions and inadequate external forcing signals at the sub-seasonal timescales and addressed notable gaps in forecasts, he said.
"This achievement addresses a long-standing technical challenge in climate change research. It offers the potential for more timely and accurate assessment of climate-related risks," Qi said.
Moreover, the new model has significantly advanced its ability to predict the atmospheric phenomenon of Madden-Julian Oscillation (MJO), extending the prediction skill of MJO from 30 to 36 days.
"Accurate MJO prediction is important for agricultural planning, disaster preparedness and risk mitigation, and long-term climate research," Qi added.
The "FuXi-Subseasonal," through its sub-seasonal forecasts of major weather processes like intense heat, severe cooling, and heavy precipitation, achieves a high level of precision unattainable by traditional technical methods, he said.
As the model advances with its cutting-edge AI capabilities, it is bound to make significant progress in addressing a broader spectrum of climate-related challenges, contributing to the empowerment of renewable energy development, construction of new types of electric power systems, ensuring agricultural food security, and achieving sustainable socio-economic transformation, Qi added.
The world needs to find more effective paths of technological innovation to address the increasingly severe global climate risks. AI holds tremendous potential in climate change risk management, said Wu Libo, a professor at Fudan University.
"With such high-end technology, we can better address the risks of climate change," Wu added.
Chinese, French experts seek multilateral future at global governance forum2024-05-08 23:26
Heavy rains ease around Houston but flooding remains after hundreds of rescues and evacuations2024-05-08 23:17
Review planned for vaccine payouts as claims soar following the pandemic2024-05-08 23:14
Legoland arrest as woman, 27, is held on suspicion of neglect after a five2024-05-08 22:35
'China is behind this': MPs lash out at Beijing over cyber2024-05-08 22:16
Sierra Nevada records snowiest day of the season2024-05-08 22:00
Mourners gather at Daniel Anjorin vigil where 142024-05-08 21:51
Brittney Griner still adjusting after Russian prison ordeal. WNBA star details experience in book2024-05-08 21:30
Workers at Stellantis plant near Detroit authorize strike in dispute over health and safety issues2024-05-08 21:11
Rublev overcomes fever and praises doctors after winning Madrid Open for the 1st time2024-05-08 21:01
Recreational marijuana backers try to overcome rocky history in South Dakota2024-05-08 23:28
Heim homers in the 9th and Lowe hits an RBI single in the 10th to lead Rangers past Royals 32024-05-08 22:55
Green councillor who shouted 'Allahu Akbar' after being elected in Leeds is accountant father2024-05-08 22:08
Heartbroken Zoe Ball pays tribute to late partner Billy Yates seven years since his passing2024-05-08 22:07
1st Chinese tour group lands in New Zealand in 3 years2024-05-08 22:02
As China and Iran hunt for dissidents in the US, the FBI is racing to counter the threat2024-05-08 21:53
DEAR JANE: My wife has ditched her razor for good2024-05-08 21:27
Russia launches drones as Ukraine marks third Easter at war2024-05-08 21:20
Man who went THREE months without a bowel movement had hardened waste stuck in his colon2024-05-08 21:17
Revealed: The mind2024-05-08 21:05