Energy-Efficient Training-Free Zero-Inflation Correction for Rainfall Forecasting with Time-Series Foundation Models
Open Access
- 12 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 8840-8850
Abstract
Accurate rainfall forecasting is essential for climate and disaster management, but precipitation exhibits extreme zero inflation that modern time-series Foundation Models (TSFMs) fundamentally cannot represent due to their continuous regression outputs. This structural mismatch causes pervasive drizzle-like false alarms, miscalibrated nonzero intensities, and severely underdetected extremes, while retraining large TSFMs is computationally prohibitive and environmentally unsustainable for most regions. We present a training-free wrapper that corrects zero inflation for frozen TSFMs without updating any parameters. Our method restores discrete zero mass using empirical occurrence statistics, aligns positive-value distributions via probability-integral transforms, and applies Generalized Pareto tail mapping for extreme-value consistency. Experiments on South Australian rainfall show substantial gains with negligible overhead (<5,ms per forecast, compared to hundreds of GPU-hours for retraining). The proposed wrapper enables carbon-neutral, globally deployable climate services and directly advances the goals of UN SDG~13 (Climate Action).Keywords
This publication has 26 references indexed in Scilit:
- Spatial-Temporal Embodied Carbon Models With Dual Carbon Attribution for Embodied Carbon Accounting of Computer SystemsIEEE Transactions on Computers, 2025
- Application of Generalized Pareto Distribution in Extreme Precipitation Analysis2025
- Accurate predictions on small data with a tabular foundation modelNature, 2025
- Learning skillful medium-range global weather forecastingScience, 2023
- Temporal Fusion Transformers for interpretable multi-horizon time series forecastingInternational Journal of Forecasting, 2021
- Green AICommunications of the ACM, 2020
- Risks from Climate Extremes Change Differently from 1.5°C to 2.0°C Depending on RarityEarth's Future, 2018
- Multi-variable error correction of regional climate modelsClimatic Change, 2013
- Statistical and dynamical downscaling of the Seine basin climate for hydro‐meteorological studiesInternational Journal of Climatology, 2007
- Probabilistic Forecasts, Calibration and SharpnessJournal of the Royal Statistical Society Series B: Statistical Methodology, 2007