TyphoFormer: Language-Augmented Transformer for Accurate Typhoon Track Forecasting
This addresses the problem of unreliable typhoon trajectory forecasting for disaster response systems, representing an incremental improvement through language augmentation of existing methods.
The paper tackles typhoon track forecasting by incorporating natural language descriptions as auxiliary prompts in a Transformer model, achieving consistent performance improvements over state-of-the-art baselines on the HURDAT2 benchmark, particularly for nonlinear path shifts and limited historical data scenarios.
Accurate typhoon track forecasting is crucial for early system warning and disaster response. While Transformer-based models have demonstrated strong performance in modeling the temporal dynamics of dense trajectories of humans and vehicles in smart cities, they usually lack access to broader contextual knowledge that enhances the forecasting reliability of sparse meteorological trajectories, such as typhoon tracks. To address this challenge, we propose TyphoFormer, a novel framework that incorporates natural language descriptions as auxiliary prompts to improve typhoon trajectory forecasting. For each time step, we use Large Language Model (LLM) to generate concise textual descriptions based on the numerical attributes recorded in the North Atlantic hurricane database. The language descriptions capture high-level meteorological semantics and are embedded as auxiliary special tokens prepended to the numerical time series input. By integrating both textual and sequential information within a unified Transformer encoder, TyphoFormer enables the model to leverage contextual cues that are otherwise inaccessible through numerical features alone. Extensive experiments are conducted on HURDAT2 benchmark, results show that TyphoFormer consistently outperforms other state-of-the-art baseline methods, particularly under challenging scenarios involving nonlinear path shifts and limited historical observations.