En breve
Los reanálisis atmosféricos globales como ERA5 presentan sesgos orográficos y costeros sistemáticos que distorsionan modelos hidrológicos y de riesgo. Integrar la red de estaciones meteorológicas de AVAMET en una topología de grafo espacial mediante GraphSAGE y Jumping Knowledge permite corregir múltiples variables de forma simultánea. Bajo una estricta partición cronológica, el enfoque en grafos reduce el error hasta en un 81% en presión, humedad, temperatura y viento frente a modelos clásicos, delimitando a su vez las fronteras operativas en precipitación extrema.
Contribución
Un marco de post-procesamiento multivariable mediante redes neuronales en grafos que captura la topología espacial de vecindad y las dependencias entre variables para corregir sesgos de ERA5, evaluado bajo particiones cronológicas sin fugas, intervalos de incertidumbre y robustez estacional.
Resultado principal
GraphSAGE con Jumping Knowledge reduce el RMSE y el MAE en seis variables no pluviométricas (presión superficial, humedad relativa, temperatura a 2 m, velocidad, dirección y ráfaga de viento) hasta en un 81% respecto a modelos clásicos y tabulares, mientras que la precipitación extrema sigue siendo un desafío abierto.
Modelos y datos
Elementos distintivos
Modelos y métodos
- GraphSAGE + Jumping Knowledge
- Random Forest reference
- Oracle classical reference
Datos y evaluación
- ERA5 reanalysis (ECMWF)
- AVAMET weather station network (Valencian Community)
Resumen del autor
Resumen del artículo
Global meteorological reanalyses such as ERA5 provide spatially coherent atmospheric fields, yet sub-grid orography and complex coastal dynamics induce systematic local biases that limit their direct utility in regional hydrology, wildfire risk assessment, renewable energy, and agriculture. While traditional bias correction approaches operate variable-by-variable and tabular machine-learning baselines neglect spatial topology, this study introduces a multivariable graph-based post-processing framework designed to model both spatial-neighborhood structure and inter-variable physical dependencies. Using ground observations from the dense AVAMET weather station network across the Valencian Community (a Western Mediterranean region with complex terrain prone to severe convective instability), station records are projected onto the ERA5 grid to train a GraphSAGE architecture with Jumping Knowledge under strict, leakage-free chronological validation splits. The graph model is benchmarked against raw ERA5, an oracle classical reference, and a fixed Random Forest baseline using block-bootstrap uncertainty estimation, fixed-window seasonal robustness diagnostics, and spatial and cross-variable consistency evaluations. On the temporal test partition, GraphSAGE+JK achieves substantial error reductions across six non-precipitation variables—cutting RMSE and MAE for surface pressure, relative humidity, 2-m temperature, wind speed, wind direction, and maximum wind gust by up to 81% relative to classical models. Conversely, precipitation remains an unresolved challenge: the graph model does not improve aggregate pointwise accuracy or high-threshold extreme occurrence detection. These findings confirm the effectiveness of graph neural networks for local predictive bias correction of continuous meteorological variables while highlighting localized precipitation extremes as a key open frontier.
Citar este trabajo
BibTeX
@article{semper2026graph,
title = {Graph-based multivariable bias correction of meteorological variables under strict temporal validation in a western mediterranean region prone to atmospheric instability},
author = {Marc Semper and Manuel Curado and Jose F. Vicent},
journal = {Journal of Computational Science},
year = {2026},
eid = {102988},
doi = {10.1016/j.jocs.2026.102988}
}Comprueba siempre el registro editorial para verificar los datos finales de volumen y páginas antes de citar.