# AI-driven hurricane forecasting advancements > Live situation record from CLSTR: https://clstr.news/situations/ai-driven-hurricane-forecasting-advancements > Updated: 2026-08-05T19:42:42.000Z. Sources: 9. Developments: 2. In late July 2026, Chinese researchers unveiled an AI‑based forecasting system that integrates the FuXi weather model with realistic ensemble generation to markedly improve hurricane track predictions. Tests on dozens of tropical cyclones showed the system outperformed leading global ensemble models and could be adapted to other hazardous weather events. A week later, DeepMind announced WeatherNext, an AI model that extends forecast capability by predicting both intensity and track a full day earlier than existing models. In a trial on Hurricane Melissa, WeatherNext correctly anticipated rapid intensification and landfall, giving the U.S. National Hurricane Center extra time for warnings and evacuations. The model leverages low‑resolution data to generate thousands of scenarios and involves collaboration with multiple national weather agencies. On 5 August 2026 DeepMind and Google Research released the WeatherNext code and model weights as open‑source software. The system can generate a 15‑day forecast in under a minute on a TPU and produces unified track‑and‑intensity predictions up to a day ahead of operational models. Early adopters such as the U.S. National Hurricane Center, the Cooperative Institute for Research in the Atmosphere and the UK Met Office have begun testing the tool, noting that the extra lead time could improve preparedness and reduce casualties. Together, these developments illustrate a rapid international push to harness artificial intelligence for more accurate and earlier hurricane forecasts, enhancing early‑warning systems and disaster mitigation worldwide. ## Claims - WeatherNext can predict cyclone track and intensity up to a day earlier than existing operational models. (corroborated by 5 sources) - The model was trained on about 20 TB of global atmospheric data and historic storm records. (corroborated by 5 sources) - WeatherNext can generate a 15‑day forecast in less than a minute on a TPU. (corroborated by 4 sources) - The project involved collaboration with Google DeepMind, Google Research, the U.S. National Hurricane Center, the Cooperative Institute for Research in the Atmosphere and the UK Met Office. (corroborated by 4 sources) - WeatherNext’s code and model weights have been released as open‑source on GitHub. (corroborated by 3 sources) - In tests, WeatherNext correctly forecast the rapid intensification and landfall of Hurricane Melissa, giving authorities extra warning time. (corroborated by 3 sources) - Mike Brennan, director of the U.S. National Hurricane Center, said an extra day of warning could improve evacuations and reduce risk to communities. (corroborated by 2 sources) - The model’s forecast skill represents roughly a decade of progress condensed into a single AI system. (corroborated by 2 sources) ## Timeline ### 2026-08-05: DeepMind's WeatherNext AI adds a day to cyclone forecasts DeepMind's WeatherNext AI predicts cyclone tracks and intensity a day earlier, offers 15‑day forecasts in minutes, is open‑source, and has been tested on Hurricane Melissa, improving early warnings. 9 sources. https://clstr.news/cluster/deepminds-weathernext-ai-model-improves-hurricane-forecasts-by-one-day ### 2026-07-29: China's AI System Boosts Hurricane Track Forecast Accuracy Chinese scientists unveiled an AI system that outperforms global models in forecasting hurricane tracks, speed and direction, promising better early warnings. 2 sources. https://clstr.news/cluster/chinas-ai-system-boosts-hurricane-track-forecast-accuracy --- Cite as: AI-driven hurricane forecasting advancements. CLSTR, https://clstr.news/situations/ai-driven-hurricane-forecasting-advancements