AI in climate science
Artificial intelligence (AI) and machine learning (ML) have demonstrated potential for their application in weather forecasting, the crossovers with climate science suggests that similar progress is possible in climate modelling.
Climate models are numerical representations of the Earth system (including components such as the atmosphere, ocean and land) that are used to explore long-term changes to the underlying statistical distributions that govern day-to-day weather.
Developments in climate models have typically come via improved scientific understanding and increased computational power, however the use of AI and ML may offer further opportunities for enhancing the representation of small-scale processes and better capturing localised impacts and/or extreme events.
Although the application of AI and ML in climate modelling is still developing, the new opportunities this offers is none-the-less highly promising and is an area of active research at the Met Office.
Through the AI4 Climate project, we’re exploring the application of cutting-edge AI and ML techniques to advance climate science and deliver improved climate information more efficiently.
The AI4Climate project is a core element of our strategic journey to deliver trusted, world-leading weather and climate intelligence through the optimal blend of simulation, data science, and AI.
AI4 Climate is funded by the UK Government’s Department for Science, Innovation and Technology (DSIT) through the International Science Partnerships Fund (ISPF) and sits under the Met Office’s National Capability AI (NCAI) Programme.