REE-TTT: Highly Adaptive Radar Echo Extrapolation Based on Test-Time Training

2026-01-04

arXiv.org

AI Summary

This work addresses the limited generalization of existing radar echo extrapolation methods under cross-regional and extreme precipitation scenarios, primarily due to their reliance on static model parameters and high-quality local training data. To overcome this, the authors propose a Spatio-Temporal Test-Time Training (ST-TTT) module that dynamically adapts the model during inference to accommodate non-stationary meteorological distributions. The key innovation lies in replacing the conventional linear projection in standard test-time training with a task-specific spatio-temporal attention mechanism, enabling efficient and adaptive representation of precipitation characteristics. Experimental results demonstrate that the proposed approach significantly outperforms state-of-the-art models in cross-regional extreme precipitation forecasting, achieving notable improvements in both prediction accuracy and generalization capability.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Precipitation nowcasting is critically important for meteorological forecasting. Deep learning-based Radar Echo Extrapolation (REE) has become a predominant nowcasting approach, yet it suffers from poor generalization due to its reliance on high-quality local training data and static model parameters, limiting its applicability across diverse regions and extreme events. To overcome this, we propose REE-TTT, a novel model that incorporates an adaptive Test-Time Training (TTT) mechanism. The core of our model lies in the newly designed Spatio-temporal Test-Time Training (ST-TTT) block, which replaces the standard linear projections in TTT layers with task-specific attention mechanisms, enabling robust adaptation to non-stationary meteorological distributions and thereby significantly enhancing the feature representation of precipitation. Experiments under cross-regional extreme precipitation scenarios demonstrate that REE-TTT substantially outperforms state-of-the-art baseline models in prediction accuracy and generalization, exhibiting remarkable adaptability to data distribution shifts.

Problem

• Radar Echo Extrapolation
• Precipitation Nowcasting
• Generalization
• Data Distribution Shift
• Test-Time Training

Innovation

• Test-Time Training
• Radar Echo Extrapolation
• Spatio-temporal Attention
• Precipitation Nowcasting
• Domain Adaptation