Science & Tech · Science & Environment · 31 mins ago
AI models forecast Typhoon Champi's path better than conventional systems
AI models forecast Typhoon Champi's track more accurately than conventional physics-based systems, which calculate weather using data and physical laws.
Champi formed over the Pacific on Oct.
15 and initially moved west; by Oct.
19, conventional forecasts mostly expected it to approach Taiwan and then China.
AI models instead predicted a northward turn near Okinawa, and the typhoon later curved sharply after approaching Japan's Nansei Islands.
Japan's Meteorological Agency mainly uses conventional models but also refers to external AI forecasts, while private service Weathernews provides AI track forecasts to paying subscribers.
Weathernews says its forecasts for last year's first 26 typhoons had about 30 percent smaller track errors than physics-based models.
AI can help people prepare earlier: an agricultural business in Ibaraki used Weathernews forecasts to install flood barriers and arrange staff shifts about a week before Typhoon Dujuan approached the Kanto region in September.
Predicting storm strength remains a challenge, making it harder to forecast rainfall and wind speeds, and experts say the agency must consider how AI can support disaster-prevention information.
AI models forecast Typhoon Champi’s northward turn more accurately than conventional physics-based models, which mostly predicted it would approach Taiwan and then China.
Champi formed over the Pacific Ocean on Oct. 15 and later curved sharply after approaching the Nansei Islands.
Japan’s Meteorological Research Institute says AI can predict large-scale atmospheric flows that shape typhoon tracks.
Experts say AI models still struggle to forecast typhoon intensity, making rainfall and wind predictions difficult.
Weathernews has offered AI-generated typhoon track forecasts to paid subscribers since last year.
- Who
- Weathernews and Japan’s Meteorological Agency use or study AI forecasts; the Meteorological Research Institute assessed their performance.
- What
- AI models forecast Typhoon Champi’s track better than conventional physics-based models.
- When
- Champi formed on Oct. 15; forecasts were compared as of Oct. 19. The article was published on Nov. 15, 2026.
- Where
- Champi formed over the Pacific Ocean and later turned after approaching the Nansei Islands.
- Why
- AI models learn patterns from past weather data and can forecast large-scale atmospheric flows that affect typhoon tracks.
This story does not have two clearly opposing sides.
Weathernews began providing paid subscribers with AI-generated typhoon track forecasts.
Typhoon Champi formed over the Pacific Ocean and initially moved westward.
Conventional forecasts mostly projected that Champi would approach Taiwan before heading toward China, while AI models forecast a northward track near Okinawa and a curve over the East China Sea.
Champi curved sharply, following the general track projected by AI models.
- Typhoon
- Champi was the year’s 30th typhoon.
- Formation date
- Oct. 15
- Forecast comparison
- As of Oct. 19, conventional forecasts mostly projected a track toward Taiwan and China.
- AI forecast
- A northward track near Okinawa, curving over the East China Sea
- Weathernews track forecasts
- Available to paid subscribers since last year
What people are saying
AI excels at forecasting large-scale atmospheric flows, including the Pacific high-pressure system and westerlies that affect typhoon tracks, and accurately predicted the timing of the turn,
cannot be ignored. We need to consider how to use them to help provide disaster prevention information,
We can improve accuracy by making the most effective use of AI,