Multivariate probabilistic forecasting using Bayesian model averaging and copulas

Abstract

We propose a method for post-processing an ensemble of multivariate forecasts in order to obtain a joint predictive distribution of weather. Our method utilizes existing univariate post-processing techniques, in this case ensemble Bayesian model averaging (BMA), to obtain estimated marginal distributions. However, implementing these methods individually offers no information regarding the joint distribution. To correct this, we propose the use of a Gaussian copula, which offers a simple procedure for recovering the dependence that is lost in the estimation of the ensemble BMA marginals. Our method is applied to 48-h forecasts of a set of five weather quantities using the 8-member University of Washington mesoscale ensemble. We show that our method recovers many well-understood dependencies between weather quantities and subsequently improves calibration and sharpness over both the raw ensemble and a method which does not incorporate joint distributional information.

17 pages, 4 figures

References in corpus (2)

• Ensemble model output statistics for wind vectors
• Probabilistic quantitative precipitation field forecasting using a two-stage spatial model

Cited by in corpus (31)

• Wind Energy: Forecasting Challenges for Its Operational Management
• Uncertainty Quantification in Complex Simulation Models Using Ensemble Copula Coupling
• Log-normal distribution based EMOS models for probabilistic wind speed forecasting
• Spatial postprocessing of ensemble forecasts for temperature using nonhomogeneous Gaussian regression
• Probabilistic wind speed forecasting using Bayesian model averaging with truncated normal components
• A similarity-based implementation of the Schaake shuffle
• Generation of scenarios from calibrated ensemble forecasts with a dual ensemble copula coupling approach
• Joint probabilistic forecasting of wind speed and temperature using Bayesian model averaging
• Comparison of multivariate post-processing methods using global ECMWF ensemble forecasts
• Probabilistic temperature forecasting based on an ensemble AR modification
• Gaussian copula modeling of extreme cold and weak-wind events over Europe conditioned on winter weather regimes
• Forecasting: theory and practice
• Generative machine learning methods for multivariate ensemble post-processing
• Bivariate ensemble model output statistics approach for joint forecasting of wind speed and temperature
• Probabilistic Temperature Forecasting with a Heteroscedastic Autoregressive Ensemble Postprocessing model
• Combining low-dimensional ensemble postprocessing with reordering methods
• Multivariate discrete copulas, with applications in probabilistic weather forecasting
• Multivariate Forecasting Evaluation: On Sensitive and Strictly Proper Scoring Rules
• Clustering-based spatial interpolation of parametric post-processing models
• Spatio-Temporal Forecasting by Coupled Stochastic Differential Equations: Applications to Solar Power
• Generating Synthetic Rainfall Fields by R-vine Copulas Applied to Seamless Probabilistic Predictions
• Rapid adjustment and post-processing of temperature forecast trajectories
• A Composite-Loss Graph Neural Network for the Multivariate Post-Processing of Ensemble Weather Forecasts
• Copula Averaging for Tail Dependence in Insurance Claims Data
• Probabilistic Forecasting of Temporal Trajectories of Regional Power Production - Part 1: Wind
• Ensemble Copula Coupling as a Multivariate Discrete Copula Approach
• Statistical models for short and long term forecasts of snow depth
• Implicit Generative Copulas
• Ensemble size dependence of the logarithmic score for forecasts issued as multivariate normal distributions
• How to Compare Copula Forecasts?
• Using published bid/ask curves to error dress spot electricity price forecasts