Tired of ads? Enjoy an ad-free experience by signing up.
👩‍🍳 How we use AI at Tech in Asia, thoughtfully and responsibly.
🧔‍♂️ A friendly human may check it before it goes live. More news here

Huawei’s AI weather model ranks high in China test

China’s Meteorological Administration (CMA) is testing 14 AI models to improve weather forecasting.

Huawei’s Pangu-Weather system has advanced notably, moving from seventh place in January to second in the latest performance rankings.

The CMA assesses these models based on key metrics including temperature, wind speed, and humidity, with daily updated scores.

Models that perform well will be prioritized for deployment by provincial weather bureaus and will receive access to official weather data.

Other significant models in the trial include Fuxi from Fudan University, Puyun from Meta Carbon Co., and Sphere Fusion Forecast, developed by the CMA, Tsinghua University, and Nvidia.

🔗 Source: Bloomberg


🧠 Food for thought

1️⃣ AI weather forecasting builds on decades of computational advancement

Weather prediction has been one of computing’s earliest and most persistent challenges, with each technological leap bringing incremental improvements in accuracy.

China’s testing of 14 different AI models continues a tradition that began in the 1950s when ENIAC produced the first computerized weather forecast, taking 24 hours to predict just 24 hours of weather 1.

The involvement of tech giants like Huawei, Google, and NVIDIA in weather forecasting represents the latest chapter in a story where computational power has been the limiting factor in prediction accuracy.

The 99% detection accuracy achieved by recent AI systems for specific weather patterns highlights how deep learning techniques are finally overcoming computational barriers that have limited traditional numerical weather prediction 1.

This progression from basic computer modeling to sophisticated AI systems reflects the increase in processing capability needed to handle the immense complexity of atmospheric physics.

2️⃣ Weather AI development thrives on cross-sector collaboration

China’s weather AI testing program reveals a pattern of collaboration between government agencies, academic institutions, and technology companies that has become essential for advancement in this field.

Notable examples include Huawei’s Pangu-Weather, Fudan University’s Fuxi, and Sphere Fusion Forecast—jointly developed by China’s state weather agency, Tsinghua University, and US chipmaker NVIDIA 1.

Recent Huawei developments

Stay ahead in Asia’s tech landscape

You've reached your 2 free content limit for the month. Sign up for free to read the full story.

🏄 For casual readers / 👶 Free

Basic

US$0

Free forever

Get instant access to this article and more every month

0 premium content

Unlimited news briefs

5

5 articles

Ad-free reading experience

Just US$0 per day

⌛Sign up in 20s. No payment details needed.

📖 For learners / 👍 Starter

Lite

US$4.92/month

Billed annually at US$59/year

Get instant access to this article and more every month

4

4 premium content

Unlimited news briefs & articles

Ad-free reading experience

Just US$0.17 per day

Cancel anytime

Our subscriber community includes professionals from these companies:

Stay updated on the go with our mobile app.

Get latest insights with smoother, more personalized experience through TIA mobile app.