对比三种深度学习气候模型，找出能稳定预测十年的最优设计
Exploring Design Choices for Autoregressive Deep Learning Climate Models
- 系统测试自回归训练步数、模型容量和预报变量的影响
- 部分模型实现10年滚动预测，且统计特性与真实数据一致
- SFNO对超参数最不敏感，但结果仍受随机种子影响
深度学习模型在中短期天气预测中表现优异，但在14天以上的模拟中常出现物理不一致性。相比之下，少数大气模型可稳定运行数十年，但其关键设计机制尚不明确。本研究定量比较了三种主流的DL-MWP架构——FourCastNet、SFNO和ClimaX——在5.625°分辨率的ERA5再分析数据上的长期稳定性。通过系统评估自回归训练步数、模型容量及预报变量的选择，识别出可实现稳定10年滚动预测并保持参考数据统计特性的配置。值得注意的是，SFNO对超参数变化具有最强鲁棒性，但所有模型的稳定性仍受随机种子和预报变量组合的影响。
原文摘要 · Abstract (English)
Deep Learning models have achieved state-of-the-art performance in medium-range weather prediction but often fail to maintain physically consistent rollouts beyond 14 days. In contrast, a few atmospheric models demonstrate stability over decades, though the key design choices enabling this remain unclear. This study quantitatively compares the long-term stability of three prominent DL-MWP architectures - FourCastNet, SFNO, and ClimaX - trained on ERA5 reanalysis data at 5.625° resolution. We systematically assess the impact of autoregressive training steps, model capacity, and choice of prognostic variables, identifying configurations that enable stable 10-year rollouts while preserving the statistical properties of the reference dataset. Notably, rollouts with SFNO exhibit the greatest robustness to hyperparameter choices, yet all models can experience instability depending on the random seed and the set of prognostic variables
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。