A Composite-Loss Graph Neural Network for the Multivariate Post-Processing of Ensemble Weather Forecasts

Abstract

Ensemble forecasting systems have advanced meteorology by providing probabilistic estimates of future states. Nonetheless, systematic biases often persist, making statistical post-processing essential. Traditional parametric post-processing techniques and machine learning-based methods can produce calibrated predictive distributions at specific locations and lead times, yet often struggle to capture dependencies across forecast dimensions. To address this, multivariate post-processing methods-such as ensemble copula coupling and the Schaake shuffle-are widely applied in a second step to restore realistic inter-variable or spatio-temporal dependencies. The aim of this study is the multivariate post-processing of ensemble forecasts using a graph neural network (dualGNN) trained with a composite loss function that combines the energy score (ES) and the variogram score (VS). The method is evaluated on two datasets: WRF-based solar irradiance forecasts over northern Chile and ECMWF visibility forecasts for Central Europe. The dualGNN consistently outperforms all empirical copula-based post-processed forecasts and shows significant improvements compared to graph neural networks trained solely on either the continuous ranked probability score or the ES, according to the evaluated multivariate verification metrics. Furthermore, for the WRF forecasts, the rank-order structure of the dualGNN forecasts captures valuable dependency information, enabling a more effective restoration of spatial relationships than either the raw numerical weather prediction ensemble or historical observational rank structures. Notably, incorporating VS into the loss function improved the univariate performance for both target variables compared to training on ES alone. Moreover, for the visibility forecasts, the ES-VS combination even outperformed the strongest calibrated reference in terms of univariate performance.

arXiv comment30 pages, 16 figures, 3 tables

References in corpus (13)

• Graph Neural Network for Traffic Forecasting: A Survey
• Neural networks for post-processing ensemble weather forecasts
• Uncertainty Quantification in Complex Simulation Models Using Ensemble Copula Coupling
• Statistical Postprocessing for Weather Forecasts -- Review, Challenges and Avenues in a Big Data World
• Multivariate probabilistic forecasting using Bayesian model averaging and copulas
• Post-processing numerical weather prediction ensembles for probabilistic solar irradiance forecasting
• Similarity-based semi-local estimation of EMOS models
• Comparison of multivariate post-processing methods using global ECMWF ensemble forecasts
• Generative machine learning methods for multivariate ensemble post-processing
• A two-step machine learning approach to statistical post-processing of weather forecasts for power generation
• Machine learning-based probabilistic forecasting of solar irradiance in Chile
• Clustering-based spatial interpolation of parametric post-processing models
• Enhancing multivariate post-processed visibility predictions utilizing CAMS forecasts