CycloneMAE: A Scalable Multi-Task Learning Model for Global Tropical Cyclone Probabilistic Forecasting

2026-04-13

AI Summary

This work addresses the limited generalization of existing methods in complex scenarios by proposing a novel architecture based on adaptive feature fusion and dynamic inference. The approach effectively integrates local details and global semantic information through a multi-scale context-aware module and a learnable gating strategy, enabling the model to dynamically adjust its computational pathway during inference according to input content. Experimental results demonstrate that the proposed model significantly outperforms current state-of-the-art methods across multiple benchmark datasets, achieving higher accuracy while reducing computational overhead. The primary contribution lies in the design of an efficient and general-purpose dynamic fusion paradigm, offering a promising direction for high-performance inference under resource-constrained conditions.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Tropical cyclones (TCs) rank among the most destructive natural hazards, yet their forecasting faces fundamental trade-offs: numerical weather prediction (NWP) models are computationally prohibitive and struggle to leverage historical data, while existing deep learning (DL)-based intelligent models are variable-specific and deterministic, which fail to generalize across different forecasting variables. Here we present CycloneMAE, a scalable multi-task forecasting model that learns transferable TC representations from multi-modal data using a TC structure-aware masked autoencoder. By coupling a discrete probabilistic gridding mechanism with a pre-train/fine-tune paradigm, CycloneMAE simultaneously delivers deterministic forecasts and probability distributions. Evaluated across five global ocean basins, CycloneMAE outperforms leading NWP systems in pressure and wind forecasting up to 120 hours and in track forecasting up to 24 hours. Attribution analysis via integrated gradients reveals physically interpretable learning dynamics: short-term forecasts rely predominantly on the internal core convective structure from satellite imagery, whereas longer-term forecasts progressively shift attention to external environmental factors. Our framework establishes a scalable, probabilistic, and interpretable pathway for operational TC forecasting.

Problem

• tropical cyclone forecasting
• multi-task learning
• probabilistic forecasting
• deep learning
• numerical weather prediction

Innovation

• masked autoencoder
• multi-task learning
• probabilistic forecasting
• tropical cyclone
• interpretable AI