Atmosphere-Ocean-Terrain Coupled Ensemble Forecast Model Improves Forecasts of Abnormally Deflecting Tropical Cyclones

ICLR 2026 Conference Submission20296 Authors

Keywords: Multimodal, Deep learning, Tropical cyclone prediction, Atmosphere-ocean-terrain coupling

TL;DR: This study constructs the multi-source AOT-TCs dataset (integrating ocean, atmosphere, and terrain variables) and proposes the AOT-TCNet model with atmosphere-ocean-terrain coupling, achieving state-of-the-art prediction.

Abstract: Deep learning-based tropical cyclone (TC) forecasting methods have demonstrated significant potential and application advantages, as they feature much lower computational cost and faster operation speed than numerical weather prediction models. However, existing deep learning methods still have key limitations: they can only process a single type of sequential trajectory data or homogeneous meteorological variables, and fail to achieve accurate forecasting of abnormal deflected TCs. To address these challenges, we present two groundbreaking contributions. First, we have constructed a multimodal and multi-source dataset named AOT-TCs for tropical cyclone forecasting in the Northwest Pacific basin. As the first dataset of its kind, it innovatively integrates heterogeneous variables from the atmosphere, ocean, and land, thus obtaining a comprehensive and information-rich meteorological dataset. Second, based on the AOT-TCs dataset, we propose a forecasting model that can handle both normal and abnormally deflected TCs. This is the first TC forecasting model to adopt an explicit atmosphere-ocean-terrain coupling architecture, enabling it to effectively capture complex interactions across physical domains. Extensive experiments on all TC cases in the Northwest Pacific from 2017 to 2024 show that our model achieves state-of-the-art performance in TC forecasting: it not only significantly improves the forecasting accuracy of normal TCs but also breaks through the technical bottleneck in forecasting abnormally deflected TCs. Project website:https://anonymous.4open.science/r/AOT-TC-111F.

Primary Area: neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)

Submission Number: 20296