用自监督学习提升多时间尺度气象预测精度
Adaptive Spatio-Temporal Graphs with Self-Supervised Pretraining for Multi-Horizon Weather Forecasting
- 构建自适应时空图网络，融合图神经网络与自监督预训练
- 在ERA5和MERRA-2数据上超越传统数值模型与深度学习方法
- 适合需要少标注数据的气象预测系统研发人员
由于大气系统的固有时空复杂性，精准可靠的天气预报仍是重大挑战。本文提出一种新颖的自监督学习框架，利用时空结构提升多变量气象预测能力。模型结合图神经网络（GNN）进行空间推理、自监督预训练方案实现表征学习，并引入时空自适应机制以增强跨不同预报时长的泛化能力。在ERA5和MERRA-2再分析数据集上的大量实验表明，该方法性能优于传统数值天气预报（NWP）模型及近期深度学习方法。对北京和上海的定量评估与可视化分析验证了模型捕捉细微气象特征的能力。所提框架为未来数据驱动的天气预报系统提供了可扩展、标签高效的技术路径。
原文摘要 · Abstract (English)
Accurate and robust weather forecasting remains a fundamental challenge due to the inherent spatio-temporal complexity of atmospheric systems. In this paper, we propose a novel self-supervised learning framework that leverages spatio-temporal structures to improve multi-variable weather prediction. The model integrates a graph neural network (GNN) for spatial reasoning, a self-supervised pretraining scheme for representation learning, and a spatio-temporal adaptation mechanism to enhance generalization across varying forecasting horizons. Extensive experiments on both ERA5 and MERRA-2 reanalysis datasets demonstrate that our approach achieves superior performance compared to traditional numerical weather prediction (NWP) models and recent deep learning methods. Quantitative evaluations and visual analyses in Beijing and Shanghai confirm the model's capability to capture fine-grained meteorological patterns. The proposed framework provides a scalable and label-efficient solution for future data-driven weather forecasting systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。