China has announced a series of new initiatives to strengthen the use of artificial intelligence in meteorological disaster prevention and expand international cooperation on early warning systems. The announcements were made at a meteorology-themed forum held during the 2026 World Artificial Intelligence Conference in Shanghai.

A key milestone was the launch of the China-Thailand Joint Laboratory for Intelligent Prediction and Early Warning of Meteorological Disasters. According to the China Meteorological Administration (CMA), it is the world's first bilateral international laboratory dedicated to AI-driven meteorological applications.

The joint laboratory will focus on developing core technologies for subseasonal-to-seasonal intelligent forecasting and early warning, while serving as an international demonstration platform in support of the United Nations' "Early Warnings for All" initiative. It also aims to promote AI meteorological technology sharing, scientific collaboration and talent training across Southeast Asia and Belt and Road partner countries.

The CMA said the laboratory will also draw on the MAZU early-warning solution. MAZU—short for Multi-hazard, Alert, Zero-gap and Universal—is China’s cloud-based AI early-warning system. It aims to provide timely and convenient weather and climate services while supporting multi-hazard risk reduction across regions.

Also at the forum, the “Djibouti 2.0” version of the MAZU meteorological early-warning solution was officially delivered. The upgraded system integrates monitoring, forecasting, and warning functions and is designed to improve early-warning services in high-impact areas with complex conditions.

In addition, China released the Fenghe meteorological service large language model and launched a global open-source plan at the forum. The plan aims to promote open sharing, strengthen international cooperation on disaster risk reduction, and broaden access to AI-enabled meteorological services.