pipette
ESEspañol

Predicting regional gray swans via translocation: AI weather models and Dubai’s unprecedented 2024 rainfall

Y. Qiang Sun, Pedram Hassanzadeh, Tiffany A. Shaw, Hamid A. Pahlavan, Adam Marchakitus

Peer-reviewed journalReal-world use

In the authors' words

This journal does not let us republish the full abstract. Here are the two sentences Pipette selected, quoted from it. Read the rest at the publisher.

Main result
These findings demonstrate the potential of AI models to forecast “regional” gray swans and the opportunity to improve them through understanding the mechanisms behind their successes/limitations.
Limitation the authors admit
Even events within the global distribution’s tail are poorly forecasted, which is not only due to data imbalance (generalization error) but also spectral bias (optimization error).

Appeared: Friday, October 9. Science Advances. Peer-reviewed journal.

DOI: 10.1126/sciadv.ady9406