Preprints
https://doi.org/10.5194/egusphere-2026-6594
https://doi.org/10.5194/egusphere-2026-6594
16 Nov 2026
 | 16 Nov 2026
Status: this preprint is open for discussion and under review for Geoscientific Model Development (GMD).

A physically constrained framework for reconstructing high-resolution solar irradiance from accumulated radiation in machine-learning weather forecasts

Zekai Dai, Man Wang, Yongwei Wang, Yuanjian Yang, Xindin Li, Xiaoying Jiang, Yajun Wang, and Jiangwei Ji

Abstract. Machine-learning weather prediction (MLWP) supports global forecasting, but solar radiation is often provided on coarse grids as multihour accumulations, creating a scale mismatch with local applications. We present SolarFINE, a physically constrained hierarchical framework that converts 0.25° six-hour accumulated radiation and concurrent meteorological states to surface solar irradiance at 0.05° and 10-min resolution. It reconstructs hourly coarse-grid irradiance from solar geometry and meteorological states under a six-hour integral-consistency constraint, then constructs an hourly high-resolution spatial background and generates subhourly variability using conditional diffusion. The temporal stage was trained on ERA5, the high-resolution stage was supervised with a satellite radiation product, and SolarFINE-T was adapted to Artificial Intelligence Forecasting System (AIFS) inputs. Evaluation covered hourly reconstruction, high-resolution spatial structure, and AIFS-driven end-to-end station performance. In controlled ERA5 experiments, SolarFINE-T achieved a daytime hourly root-mean-square error (RMSE) of 40.37 W m−2, 29.9 % lower than with solar-geometry allocation. At 0.05° and 10-min resolution, SolarFINE-J achieved an RMSE of 132.42 W m−2 and more closely reproduced the spatial power spectrum, spatial variability, and high-irradiance tail of the high-resolution reference product. In the independent station evaluation, RMSE skill scores relative to solar-geometry allocation were positive on forecast days 1–15, rising from 0.084 to 0.174. Improvements were largest and most consistent at intermediate clear-sky index. Adapting to AIFS inputs improved skill, whereas forcing hourly fields to match the original six-hour accumulation reduced it. The results indicate that MLWP-driven solar-irradiance downscaling requires exploiting atmospheric information beyond solar geometry while accounting for upstream forecast errors.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share
Zekai Dai, Man Wang, Yongwei Wang, Yuanjian Yang, Xindin Li, Xiaoying Jiang, Yajun Wang, and Jiangwei Ji

Status: open (until 11 Jan 2027)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Zekai Dai, Man Wang, Yongwei Wang, Yuanjian Yang, Xindin Li, Xiaoying Jiang, Yajun Wang, and Jiangwei Ji
Zekai Dai, Man Wang, Yongwei Wang, Yuanjian Yang, Xindin Li, Xiaoying Jiang, Yajun Wang, and Jiangwei Ji

Viewed

Total article views: 19 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
18 0 1 19 4 3
  • HTML: 18
  • PDF: 0
  • XML: 1
  • Total: 19
  • BibTeX: 4
  • EndNote: 3
Views and downloads (calculated since 16 Nov 2026)
Cumulative views and downloads (calculated since 16 Nov 2026)

Viewed (geographical distribution)

Total article views: 19 (including HTML, PDF, and XML) Thereof 19 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 17 Nov 2026
Download
Short summary
Weather forecasts often report sunlight as totals over several hours and large areas. We developed a method to turn these totals into local estimates every 10 minutes while keeping the amounts physically consistent. It reduced hourly errors by about 30 % in controlled tests and improved forecasts against independent ground observations. The method helps translate global weather forecasts into information useful for solar energy applications.
Share