Uncertainty quantification (UQ) is increasingly critical for modelling complex systems in which input parameters or environmental conditions vary unpredictably. Polynomial chaos methods offer a ...

Conformal prediction offers a robust, distribution-free framework that transforms point estimates into prediction sets or intervals by leveraging the concept of exchangeability. This framework helps ...

On 30 March 2026 a 1-day workshop will be organized at CWI by AIMET-NL, the newly initiated Dutch research network on AI for Weather & Climate. The topic of this meeting is Scientific Machine Learning ...

NOTICE: The project that is the subject of this report was approved by the Governing Board of the National Research Council, whose members are drawn from the councils of the National Academy of ...

Accurately tracking atmospheric greenhouse gases requires not only fast predictions but also reliable estimates of uncertainty. Researchers have developed a lightweight machine learning framework that ...