A breakthrough AI model, trained on over a million hours of data, could transform how people prepare for major floods and other natural disasters.

The model, Aurora, has been designed to deliver faster, more accurate, and more affordable forecasts for extreme weather, ocean waves and air quality. As climate volatility increases, rapid and reliable forecasts are crucial for disaster preparedness, emergency response, and climate adaptation.

Aurora was developed by an international team scientists based at the Microsoft AI research centre in Amsterdam, Netherlands, and Cambridge, UK, who say it could revolutionise the way we prepare for natural disasters and respond to climate change.

From deadly floods in Europe to intensifying tropical cyclones around the world, the climate crisis has made timely and precise forecasting more critical than ever. However, traditional forecasting methods rely on highly complex numerical models developed over decades, requiring powerful supercomputers and large teams of experts.

The researchers believe Aurora can help by making advanced forecasting more accessible.

Max Welling, machine learning expert at the University of Amsterdam, said: "Aurora uses state-of-the-art machine-learning techniques to deliver superior forecasts for key environmental systems - air quality, weather, ocean waves, and tropical cyclones.

"Unlike conventional methods, Aurora requires far less computational power, making high-quality forecasting more accessible and scalable - especially in regions that lack expensive infrastructure.

"Importantly, this acceleration builds on decades of foundational research and the vast datasets made available through traditional forecasting methods."

Aurora is built on a 1.3 billion parameter foundation model, trained on more than one million hours of earth system data. It has been fine-tuned to excel in a range of forecasting tasks, frequently outperforming traditional models.

AI researcher Ana Lucic, of the University of Amsterdam, said: "Development cycles that once took years can now be completed in just weeks by small engineering teams. This could be especially valuable for countries in the Global South, smaller weather services, and research groups focused on localised climate risks."

Aurora is available freely online for anyone to use. Lucic explains if someone wants to fine-tune it for a specific task, they will need to provide data for that task. "But the 'initial' training is done, we don’t need these vast datasets anymore, all the information from them is baked into Aurora already."

Although current research focuses on four applications, the researchers say Aurora is flexible and can be used for a wide range of future scenarios, such as forecasting flood risks, wildfire spread, seasonal weather trends and agricultural yields.

Welling says: ‘Its ability to process diverse data types makes it a powerful and future-ready tool."