Search papers, labs, and topics across Lattice.
The TC-Next model leverages multimodal deep learning to forecast tropical cyclone track and intensity using atmospheric kinematic and thermodynamic fields alongside infrared satellite imagery. By training exclusively on GraphCast forecasts for the Western Pacific, TC-Next achieves significant reductions in track error (15-44%) and intensity error (3-6 times lower) compared to the conventional TempestExtremes tracker. Notably, TC-Next maintains superior performance in zero-shot applications across different weather forecasting models, demonstrating its robustness and generalizability in cyclone predictions.
TC-Next outperforms traditional cyclone tracking methods by integrating multimodal data, achieving unprecedented accuracy in both track and intensity forecasts.
We present TropicalCycloneNext (TC-Next), a multimodal deep learning model that forecasts tropical cyclone track and intensity at $6$-$24$ h leads by leveraging a foundation model's forecast fields of atmospheric kinematic and thermodynamic fields and GridSat infrared satellite imagery. Trained only on GraphCast forecasts over the Western Pacific (WP), yet reliant only on generic atmospheric variables, TC-Next on GraphCast lowers track error by $15$-$44\%$ and intensity error by a factor of $3$-$6$ relative to a conventional, rule-based tracker, TempestExtremes; applied without retraining to the forecast fields of Pangu-Weather and IFS HRES, it stays ahead of TempestExtremes on both. Applied zero-shot to the generic weather fields of WeatherNext Cyclones on the 2025 WP season, TC-Next attains lower intensity error at every lead time, and lower or comparable track error, compared to that model's specialized direct tracker in a deterministic comparison. Our ablation studies show that our multimodal model is able to utilize the additional modality to improve performance in tracking errors at every lead time and in intensity prediction at longer lead times.
