GPTCast: a weather language model for precipitation nowcasting
This addresses the problem of accurate and probabilistic weather forecasting for meteorologists and related fields, representing a novel method for a known bottleneck.
This work tackled precipitation nowcasting by developing GPTCast, a generative deep-learning method that uses a GPT model to learn spatiotemporal dynamics from tokenized radar images, achieving superior results compared to state-of-the-art ensemble extrapolation methods on a 6-year radar dataset over Northern Italy.
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.