发表机构
National Taiwan University（国立台湾大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究长期自回归天气预报中误差增长问题，提出自输出微调（SOFT）策略，利用模型单步预测校准输入分布，经实验验证该策略能显著提升长期预测性能，减少误差和分布差异，推动了深度学习天气预报流程发展。
AI 中文摘要
长期天气预报是大气科学中的一项基本挑战，自回归深度学习天气预报（DLWP）已成为主要范式。尽管自回归流程具有高度可扩展性和灵活性，但在长期预测中预测误差增长迅速。本文从理论和实证角度研究了这种误差增长现象，发现其由输出误差和输入分布变化之间的反馈回路驱动，类似于蝴蝶效应。这种分布变化在推理的最早阶段就已出现。为缓解此问题，提出了自输出微调（SOFT）策略，利用模型自身的单步预测来校准第一步遇到的偏差输入分布。实验表明，SOFT在长期预测任务中取得了领先性能，显著减少了预测误差和分布差异，凸显了重新审视深度学习天气预报基本流程的重要性。
英文摘要
Long-horizon weather forecasting is a fundamental challenge in atmospheric science, for which autoregressive Deep Learning Weather Prediction (DLWP) has emerged as the primary paradigm. Although the autoregressive pipeline is highly scalable and flexible, its prediction errors grow rapidly over long forecasting horizons. In this work, we study this error growth phenomenon from both theoretical and empirical perspectives. Our analysis reveals that the growth is driven by a feedback loop between output errors and input distribution shifts. Specifically, the autoregressive process amplifies small initial output errors, which progressively corrupt subsequent input distributions, echoing the butterfly effect in atmospheric science and ultimately deteriorating forecasting accuracy over longer horizons. Furthermore, we show that this distributional shift originates at the earliest stage of inference, with out-of-distribution signatures detectable as early as the first autoregressive step. To mitigate this issue, we propose \textbf{Self-Output Fine-Tuning (SOFT)}, a plug-and-play strategy that leverages the model's own one-step predictions to calibrate the biased input distribution encountered at the first step. Extensive experiments demonstrate that, despite its simplicity, SOFT achieves state-of-the-art performance on long-horizon forecasting tasks and substantially reduces both prediction errors and distributional discrepancy. The success of SOFT highlights the importance of reexamining the fundamental pipeline of deep learning weather prediction, representing a critical pipeline advance for atmospheric science.
