Lightweight Wrappers for Adapting Time Series Foundation Models to Regional Drought Forecasting
2026-07-20 • Machine Learning
Machine Learning
AI summaryⓘ
The authors created a simple way to improve big pre-trained time series forecasting models for predicting regional climate without changing the original model itself. Their method uses two add-ons that look at the data in different ways and combine their results to make better predictions. This approach works during prediction time only, avoiding the need for expensive retraining. They tested it on climate data in South Australia and found it made forecasts noticeably more accurate while being practical for places with limited computing power.
Time Series Foundation Modelsforecastingblack-box adaptationmulti-resolution decompositionensemble learningStandardized Precipitation Evapotranspiration Indexmean squared errorblock bootstrapregional climate forecastingresource constraints
Authors
Wentao Gao, Jiuyong Li, Lin Liu, Thuc Duy Le, Jixue Liu, Yanchang Zhao, Yun Chen
Abstract
Large \emph{Time Series Foundation Models} (TSFMs) demonstrate strong zero-shot forecasting capabilities across diverse domains. However, their application to regional climate forecasting faces practical challenges: model weights are often proprietary, local training records are limited, and computational budgets are constrained, making traditional fine-tuning approaches infeasible. To address these constraints, we introduce a lightweight, black-box adaptation framework (requiring no access to backbone parameters and no backbone fine-tuning) that enhances frozen TSFMs at inference time through two plug-and-play wrappers: \textbf{SMR\textsuperscript{2}} (Stationarity aware multi-resolution Residual), which decomposes the input into multi-resolution temporal views, learns stride specific residual corrections that capture regional dynamics, then adaptively ensembles them into a single forecast, and \textbf{MBB} (Moving Block Bootstrap), which preserves temporal dependencies through block resampling and ensembles over temporally coherent residual perturbations to stabilize the point forecast. Both wrappers instantiate the same bagging style principle: they build diverse views of the input or its residuals, forecast each with the same frozen backbone, and aggregate, so all adaptation comes from inference time ensembling rather than any weight update. Evaluated on one month ahead Standardized Precipitation Evapotranspiration Index (SPEI) prediction across multiple sites in South Australia, our framework consistently improves forecasting performance across several backbone models, demonstrating up to 26\% mean squared error (MSE) reduction over the corresponding frozen backbone while enabling practical deployment in resource constrained regional forecasting systems.