AI meets climate forecasting: a new era for seasonal predictions

#Klimaatverandering, #Artificial Intelligence, #ESA

Gepubliceerd op 26 maart 2026

Predicting climate conditions months in advance remains one of the most difficult problems in Earth science. A recent study, published in npj Climate and Atmospheric Science proposes a new approach, combining artificial intelligence with probabilistic modelling to improve seasonal forecasts.

Traditional methods rely on general circulation models (GCMs), which simulate atmospheric and ocean dynamics. While physically grounded, these models are computationally expensive, limiting their scalability. Simpler statistical models are more efficient but often less reliable due to limited observational data. This trade-off has long constrained forecasting performance.

 A hybrid, data-driven approach

The new framework, developed in the context of the AI4DROUGHT project, takes a different route by learning directly from data. It combines observational records with outputs from existing climate simulations, effectively expanding the training dataset. The model is built on transformer-based neural networks and uses variational inference to represent uncertainty.

Instead of producing a single forecast, it generates probabilistic predictions, capturing a range of possible outcomes and their likelihoods. This allows the system to reflect the inherent uncertainty of climate processes rather than masking it.

Sources: