EUVIMEDTutustu EUVIMEDiin
Open access · CC BY 4.0

Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations

Alejandro J. González-Santana, Giovanny A. Cuervo-Londoño, Javier Sánchez

Electronics · 2026-04-10 · 15 (8) · 1583

DOI: 10.3390/electronics15081583 ↗

At a glance

Journal article in Electronics, published online on 2026-04-10. Written by Alejandro J. González-Santana and 2 co-authors. 41 references. The full text is freely available (open access, CC BY 4.0). Funded by: Fundación Biodiversidad.

TiivistelmäBibliografiset tiedotCiteRelated studies

Abstract (original language)

Accurate regional ocean forecasting requires models that are both computationally efficient and capable of representing predictive uncertainty. This work investigates ensemble learning strategies for sea surface temperature (SST) forecasting using Graph Neural Networks (GNNs), with a focus on how input perturbation design affects forecast skill and uncertainty representation. We adapt a GNN architecture to the Canary Islands region in the North Atlantic and implement a homogeneous ensemble approach inspired by bagging, where diversity is introduced during inference by perturbing initial ocean states rather than retraining multiple models. Several noise-based ensemble generation strategies are evaluated, including Gaussian noise, Perlin noise, and fractal Perlin noise, with systematic variation of noise intensity and spatial structure. Ensemble forecasts are assessed over a 15-day horizon using deterministic metrics (RMSE and bias) and probabilistic metrics, including the Continuous Ranked Probability Score (CRPS) and the Spread–skill ratio. The results show that, while deterministic skill remains comparable to the single-model forecast, the type and structure of input perturbations influence uncertainty representation, particularly at longer lead times. Ensembles generated with spatially coherent perturbations, such as low-resolution Perlin noise, achieve improved calibration and lower CRPS compared to purely random Gaussian perturbations. These findings highlight the role of noise structure and scale in ensemble GNN design, indicating that specifically structured input perturbations can improve ensemble diversity and calibration without additional training cost. These results provide a methodological contribution toward the study of ensemble-based GNN approaches for regional ocean forecasting.

Funding

  • Fundación Biodiversidad

Cite

APA

González-Santana, A. J., Cuervo-Londoño, G. A., & Sánchez, J. (2026). Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations. Electronics, 15(8), 1583. https://doi.org/10.3390/electronics15081583

Vancouver

González-Santana AJ, Cuervo-Londoño GA, Sánchez J. Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations. Electronics. 2026;15(8):1583. doi:10.3390/electronics15081583

BibTeX
@article{GonzlezSantana2026,
  author = {González-Santana, Alejandro J. and Cuervo-Londoño, Giovanny A. and Sánchez, Javier},
  title = {Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {8},
  pages = {1583},
  doi = {10.3390/electronics15081583}
}
Start for free →