For decades, weather ⁠prediction ⁠has relied on numerical models running on supercomputers, now AI can produce forecasts in a fraction of the time. Will it be accurate? Here's what experts are saying

Chinese-developed systems, including Shanghai AI Laboratory-developed Fengwu, Huawei's Pangu and Fudan University's Fuxi, are among a handful of AI forecasting models that researchers say can generate forecasts much faster than conventional systems while matching or surpassing them on some measures ‌of accuracy.

For decades, weather ⁠prediction ⁠has relied on numerical models running on supercomputers that simulate atmospheric physics. AI models instead learn patterns from vast archives of historical weather ​observations and can produce forecasts in a fraction of the time. The technology is increasingly being tested during typhoon season in ​East Asia, where even small improvements in track forecasts can help authorities better prepare for flooding, organise evacuations and manage potential transport disruptions.



The rise of AI weather forecasting has created a new arena of competition among technology companies, research institutes and meteorological agencies, with China emerging as one of ⁠the field's ‌leading players.

Among the best-known AI forecasting systems globally are Google's GraphCast and GenCast, Nvidia-backed FourCastNet ​and the European ​Centre for Medium-Range Weather Forecasts' AI Forecasting System, known as AIFS.

Weather Forecast

Fengwu attracted ⁠attention after developers reported it outperformed GraphCast across roughly 80% of evaluated ​weather variables and extended skilful global medium-range forecasts beyond 10 days.

"With more extreme ​weather, people need information to make decisions, both local governments, the national government, also the average person, farmers and fisherman," said Sun Zhi, the CTO of Techwind, the company responsible for Fengwu's industrial applications. "So we want to help provide better information so people can make decisions."

While AI systems are becoming an increasingly important complement to conventional forecasting because of their speed and lower computing costs, they are unlikely to fully replace traditional weather models ‌in the near future, as per Reuters report.

According to Techwind's Sun, AI models are already capable of predicting the path of typhoons — five days out from Dolphin's landfall Fengwu predicted the time and place ​it would hit ​mainland China to within 30 ⁠minutes and 30 km (19 miles) — but they still lag conventional weather forecasts in predicting the intensity of a storm and they are still untested predicting major climate developments.

"If we predict a climate change event 18 months in advance, ​people won't believe it," Sun said. "They need to know it's reliable. We need to do years of scientific research before people trust us when we say there will be an El Nino event or we say the changing temperature on the sea's surface will affect the breeding cycle of fish."

As the tech forecasters work to make their systems ever more sophisticated, the concurrent use of both methods is likely to continue for some time.