Residual-Guided Multi-Resolution Refinement of Foundation Models: A Case Study in Drought Forecasting

Wentao Gao, Jiuyong Li, Lin Liu, Thuc Duy Le, Jixue Liu, Yanchang Zhao, Yun ChenICML 2026 · OpenReview

Abstract

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.
BibTeX
@inproceedings{gao2026residual,
  author = {Wentao Gao and Jiuyong Li and Lin Liu and Thuc Duy Le and Jixue Liu and Yanchang Zhao and Yun Chen},
  title = {{Residual-Guided Multi-Resolution Refinement of Foundation Models: A Case Study in Drought Forecasting}},
  booktitle = {International Conference on Machine Learning},
  year = {2026},
  url = {https://openreview.net/forum?id=ERCbhCrHo3},
}

Loading related content...

Figure