GPTCast: a weather language model for precipitation nowcasting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911123317456896 |
|---|---|
| author | Franch, Gabriele Tomasi, Elena Wanjari, Rishabh Poli, Virginia Cardinali, Chiara Alberoni, Pier Paolo Cristoforetti, Marco |
| author_facet | Franch, Gabriele Tomasi, Elena Wanjari, Rishabh Poli, Virginia Cardinali, Chiara Alberoni, Pier Paolo Cristoforetti, Marco |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_02089 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GPTCast: a weather language model for precipitation nowcasting Franch, Gabriele Tomasi, Elena Wanjari, Rishabh Poli, Virginia Cardinali, Chiara Alberoni, Pier Paolo Cristoforetti, Marco Machine Learning Atmospheric and Oceanic Physics 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. |
| title | GPTCast: a weather language model for precipitation nowcasting |
| topic | Machine Learning Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2407.02089 |