Self-supervised, physics-constrained super-resolution for wind mapping in the absence of high-resolution training references: a case study in Brazil
GeoInformatica · 2026-12 · 30 (2)
DOI: 10.1007/s10707-026-00601-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift GeoInformatica, online erschienen am 17.11.2026. Verfasst von José Péricles Freire und 3 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidade Federal De Minas Gerais.
Abstract (Originalsprache)
Planning renewable-energy expansion at the national scale requires wind maps far more detailed than sparse meteorological networks and coarse reanalysis grids can typically offer. This study introduces PC-SRCNN, a physics-constrained, self-supervised super-resolution framework that lifts ERA5 wind fields over Brazil from a native 0.25° grid to 0.025°, folding in soft regularization terms for horizontal kinematic consistency and the logarithmic vertical wind profile. The model was evaluated against observations from 190 meteorological stations from Brazil’s INMET network across all twelve months of 2024, benchmarked against IDW, Kriging, U-Net, SRCNN, and a variant constrained only by horizontal kinematics (PC-SRCNN𝜑). The full PC-SRCNN was the only model to outperform native ERA5 with statistical significance in every month, cutting MAE by 5.6–11.0%, reaching vertical-profile R² between 0.80 and 0.87, and posting the lowest error at 133 of the 190 stations (70.0%); the PC-SRCNN𝜑 variant, in contrast, performed significantly worse than ERA5, and the purely data-driven models failed to consistently beat it. These findings show that physical regularization aids wind-field super-resolution only when it respects the vertical structure of the atmospheric boundary layer, suggesting the potential of this framework as a computationally lightweight approach for super-resolution wind mapping in settings where conventional numerical downscaling is computationally demanding.
Förderung
- Universidade Federal De Minas Gerais
Zitieren
APA
Freire, J. P., Rubio, L., Yang, J., & Velasquez, C. E. (2026). Self-supervised, physics-constrained super-resolution for wind mapping in the absence of high-resolution training references: a case study in Brazil. GeoInformatica, 30(2). https://doi.org/10.1007/s10707-026-00601-2
Vancouver
Freire JP, Rubio L, Yang J, Velasquez CE. Self-supervised, physics-constrained super-resolution for wind mapping in the absence of high-resolution training references: a case study in Brazil. GeoInformatica. 2026;30(2). doi:10.1007/s10707-026-00601-2
BibTeX
@article{Freire2026,
author = {Freire, José Péricles and Rubio, Lihki and Yang, Jin and Velasquez, Carlos E.},
title = {Self-supervised, physics-constrained super-resolution for wind mapping in the absence of high-resolution training references: a case study in Brazil},
journal = {GeoInformatica},
year = {2026},
volume = {30},
number = {2},
doi = {10.1007/s10707-026-00601-2}
}
EUVIMED