Forecast-space decomposition for intra-hour solar irradiance prediction from sky images

Complementary forecasts, one shared model.

GateFormer forecasts global horizontal irradiance (GHI) from sky imagery and recent irradiance measurements. A shared, GHI-conditioned Vision Transformer feeds two complementary predictors: one forecasts the future trajectory, while the other predicts change at the final horizon. A learned gate blends their forecasts, followed by a residual correction.

Results at a glance

Evaluated on NREL-TSI, Chilbolton, and SIRTA. Figures are from the published paper; comparisons follow its evaluation protocol.

Follow the code release

This is the paper’s project page. The implementation will be added to the GitHub repository in a future update.

Bookmark or star the repository, or choose Watch → Custom → Releases on GitHub to follow future releases.

If this work is useful to your research, please cite the paper.

@article{hamlyn2026gateformer,
  title   = {{GateFormer}: Forecast-space decomposition for intra-hour solar irradiance prediction from sky images},
  author  = {Hamlyn, David and Chaudhary, Sunny and Hare, Jonathon and Rahman, Tasmiat},
  journal = {Energy and AI},
  volume  = {26},
  pages   = {100917},
  year    = {2026},
  doi     = {10.1016/j.egyai.2026.100917},
  url     = {https://doi.org/10.1016/j.egyai.2026.100917}
}

Download BibTeX · View publication

Related research

Vision Transformers for Estimating Irradiance Using Data-Scarce Sky Images
Our earlier work on solar irradiance estimation · Energy and AI, 2025