China, on Friday, unveiled a series of artificial intelligence-powered meteorological initiatives aimed at strengthening global early warning capabilities as extreme weather becomes more frequent amid global warming.
The announcements, made at the meteorological forum of the 2026 World AI Conference and High-Level Meeting on Global AI Governance in Shanghai, included the launch of an AI weather satellite toolbox, the delivery of an upgraded early warning system to the Republic of Djibouti in Africa, and the establishment of the world's first bilateral laboratory dedicated to AI applications in meteorology.
The China Meteorological Administration launched the MAZU-FengYun Satellite AI Box, an integrated hardware and software platform that combines observations from China's Fengyun meteorological satellite system with AI.
The toolbox enables users to receive satellite data, run AI-powered weather analysis and generate forecasts locally, allowing countries with limited computing infrastructure to turn satellite observations into operational weather services.
"The toolbox provides not only a technical product, but also a practical and adaptable application capability," said Wang Jinsong, director of the National Satellite Meteorological Center.
Wang said the platform marks a new stage in China's MAZU intelligent early warning initiative, launched last year, by shifting from providing shared meteorological products to delivering AI-enabled forecasting capabilities.
China also formally delivered MAZU Djibouti 2.0, an upgraded version of its intelligent weather early warning system tailored to the East African nation.
The system combines weather-monitoring chips, forecasting models and intelligent warning terminals with AI agents already deployed in Djibouti to create an integrated monitoring, forecasting and warning platform.
According to the CMA, the upgraded system improves forecast resolution from 9 kilometers to 3 kilometers, provides three-day forecasts updated every six hours, and features one-click warning alerts and real-time interactive functions. Deployment of MAZU Djibouti 2.0 is expected to be completed by the end of this year.
China and Thailand also announced the establishment of the China-Thailand Joint Laboratory for Intelligent Prediction and Early Warning of Meteorological Disasters, the world's first bilateral laboratory focused on AI applications in meteorology.
The laboratory will develop AI technologies for subseasonal-to-seasonal forecasts of typhoons, torrential rainfall, heat waves and droughts, while serving as a regional platform for technology sharing and professional training across Southeast Asia.
"The lab seeks to establish an integrated multihazard early warning system for China and Thailand, supporting cross-border projects in sectors such as energy, agriculture and infrastructure," said Zhang Xingying, director of the CMA's Department of International Cooperation.
Jointly led by the Xiong'an Institute of Meteorological Artificial Intelligence and the Climate Center of the Thai Meteorological Department, the laboratory will bring together more than 40 experts in atmospheric science, climatology and AI.
Chalump Oonariya, the Thai co-director of the laboratory, said China's global meteorological datasets and AI models will help improve Thailand's forecasts for droughts, heavy rainfall and other weather hazards, strengthening local disaster prevention and mitigation.