GPTCast: a weather language model for precipitation nowcasting
Abstract. This work introduces GPTCast, a generative deep-learning method for ensemble nowcast of radar-based precipitation, inspired by advancements in large language models (LLMs). We employ a GPT model as a forecaster to learn spatiotemporal precipitation dynamics using tokenized radar images. The tokenizer is based on a Quantized Variational Autoencoder featuring a novel reconstruction loss tailored for the skewed distribution of precipitation that promotes faithful reconstruction of high rainfall rates. The approach produces realistic ensemble forecasts and provides probabilistic outputs with accurate uncertainty estimation. The model is trained without resorting to randomness, all variability is learned solely from the data and exposed by model at inference for ensemble generation. We train and test GPTCast using a 6-year radar dataset over the Emilia-Romagna region in Northern Italy, showing superior results compared to state-of-the-art ensemble extrapolation methods.
Status: open (until 05 Dec 2024)
Data sets
Dataset for "GPTCast: a weather language model for precipitation nowcasting" Gabriele Franch, Elena Tomasi, Chaira Cardinali, Virginia Poli, Pier Paolo Alberoni, and Marco Cristoforetti https://doi.org/10.5281/zenodo.13692016
Model code and software
Code for "GPTCast: a weather language model for precipitation nowcasting" Gabriele Franch, Elena Tomasi, and Marco Cristoforetti https://doi.org/10.5281/zenodo.13832526
Interactive computing environment
Jupyter Notebooks for "GPTCast: a weather language model for precipitation nowcasting" Gabriele Franch, Elena Tomasi, and Marco Cristoforetti https://github.com/DSIP-FBK/GPTCast/tree/main/notebooks
Viewed
Since the preprint corresponding to this journal article was posted outside of Copernicus Publications, the preprint-related metrics are limited to HTML views.
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
61 | 0 | 0 | 61 | 0 | 0 |
- HTML: 61
- PDF: 0
- XML: 0
- Total: 61
- BibTeX: 0
- EndNote: 0
Viewed (geographical distribution)
Since the preprint corresponding to this journal article was posted outside of Copernicus Publications, the preprint-related metrics are limited to HTML views.
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1