Skip to main content
zenodoopen

Dataset for "GPTCast: a weather language model for precipitation nowcasting"

<p>Dataset for "<em><strong>GPTCast: a weather language model for precipitation nowcasting</strong></em>"</p> <ul> <li>Preprint:&nbsp;<a href="https://arxiv.org/abs/2407.02089">https://arxiv.org/abs/2407.02089</a></li> <li>Code:&nbsp;<a href="https://github.com/DSIP-FBK/GPTCast">https://github.com/DSIP-FBK/GPTCast</a></li> <li>Pretrained models:&nbsp;<a href="https://doi.org/10.5281/zenodo.13594332">https://doi.org/10.5281/zenodo.13594332</a></li> </ul> <p>Version 2 of this dataset contains also the "Forecaster Test Set" (fts.tar) which includes all generated forecasts for GPTCast8x8, GPTCast16x16, and Linda, to ensure reproducibility of the results.</p>

ShareScore

40/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
4
Harmonization
4
Access
20
Reuse readiness
8
Engagement
4