用多尺度迭代修正提升气候模型预测精度，无需重训练。
Residual-Guided Multi-Resolution Refinement of Foundation Models: A Case Study in Drought Forecasting
- 基于残差引导的多分辨率迭代优化，推理时改进预测结果。
- 在南澳3个站点上，1个月预报误差降低最多18.9%。
- 适用于各类预训练时间序列模型，部署灵活无须调参。
区域气候预测对时间序列基础模型提出独特挑战，这类模型通常采用单次前向推断处理时序模式。而专业气候学家则依赖多尺度时间分析与基于系统性误差诊断的迭代修正。本文提出RGMR（残差引导的多分辨率精炼）框架，一种推理时的改进方法，可在不更新主干参数的前提下，使预训练的基础模型实现结构化的粗到细精炼。该方法应用于干旱预测任务，以标准化降水蒸散指数（SPEI）为指标，在三个南澳站点及另外三个非南澳地区均表现出色。在使用TimesFM模型时，该封装器在三个南澳站点上将一个月提前的SPEI均方误差降低最多达18.9%（平均降幅约18.7%）。整体上，RGMR为在区域气候预测流程中部署冻结的时间序列基础模型提供了一条实用路径。
原文摘要 · Abstract (English)
Regional climate prediction presents unique challenges for time series foundation models, which typically process temporal patterns through single-pass inference. Expert climatologists, in contrast, employ multi-scale temporal analysis and iterative refinement based on systematic error diagnosis. We present RGMR (Residual-Guided Multi-Resolution Refinement), an inference-time framework that adapts pre-trained foundation models to perform structured coarse-to-fine refinement for climate forecasting without updating backbone parameters. Applied to drought forecasting using the Standardized Precipitation Evapotranspiration Index (SPEI), RGMR is architecture-agnostic across the three TSFM backbones evaluated per site (TimesFM, TimeGPT, TabPFN) and consistently lowers test-set MSE on three South Australian sites and three additional regions outside South Australia. Applied to TimesFM, the wrapper reduces one-month-ahead SPEI MSE by up to 18.9\% across the three South Australian sites (mean reduction $\approx$18.7\%). Overall, RGMR provides a practical route for deploying frozen TSFMs in regional climate forecasting workflows.
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。