# TC-Next: Zero-Shot Multimodal Cyclone Forecasting

arXiv: https://arxiv.org/abs/2609.02085 · HTML: https://mlsanity.com/paper/2609.02085/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Efficient Low-rank Multimodal Fusion with Modality-Specific Factors](https://mlsanity.com/paper/1806.00064/) (2018)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [Skillful joint probabilistic weather forecasting from marginals](https://mlsanity.com/paper/2506.10772/) (2025)
- [Hurricane Forecasting: A Novel Multimodal Machine Learning Framework](https://mlsanity.com/paper/2011.06125/) (2020)
- [TCBench: A Benchmark for Tropical Cyclone Track and Intensity Forecasting at the Global Scale](https://mlsanity.com/paper/2601.23268/) (2026)
- [CycloneMAE: A Scalable Multi-Task Learning Model for Global Tropical Cyclone Probabilistic Forecasting](https://mlsanity.com/paper/2604.12180/) (2026)

## Abstract (arXiv)

We present TropicalCycloneNext (TC-Next), a multimodal deep learning model that forecasts tropical cyclone track and intensity at 6-24h leads by leveraging a foundation model's forecast of atmospheric kinematic and thermodynamic fields, along with 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 the rule-based tracker TempestExtremes; applied without retraining to Pangu-Weather and IFS HRES forecasts, it stays ahead on both. Applied zero-shot to the generic weather fields of WeatherNext Cyclones on the 2025 WP season, it attains lower average intensity error at every lead time, and lower or comparable average track error, than that model's specialized direct tracker in a deterministic comparison. Ablations show that the satellite branch lowers track error at every lead time and intensity error at longer leads. TC-Next thus gives a common, independently verifiable basis for comparing the AI forecasts that inform cyclone-warning and climate-adaptation decisions as best available science.