Generative machine learning methods for multivariate ensemble post-processing

Abstract

Ensemble weather forecasts based on multiple runs of numerical weather prediction models typically show systematic errors and require post-processing to obtain reliable forecasts. Accurately modeling multivariate dependencies is crucial in many practical applications, and various approaches to multivariate post-processing have been proposed where ensemble predictions are first post-processed separately in each margin and multivariate dependencies are then restored via copulas. These two-step methods share common key limitations, in particular the difficulty to include additional predictors in modeling the dependencies. We propose a novel multivariate post-processing method based on generative machine learning to address these challenges. In this new class of nonparametric data-driven distributional regression models, samples from the multivariate forecast distribution are directly obtained as output of a generative neural network. The generative model is trained by optimizing a proper scoring rule which measures the discrepancy between the generated and observed data, conditional on exogenous input variables. Our method does not require parametric assumptions on univariate distributions or multivariate dependencies and allows for incorporating arbitrary predictors. In two case studies on multivariate temperature and wind speed forecasting at weather stations over Germany, our generative model shows significant improvements over state-of-the-art methods and particularly improves the representation of spatial dependencies.

References in corpus (18)

• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• Generative Moment Matching Networks
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Statistical Postprocessing for Weather Forecasts -- Review, Challenges and Avenues in a Big Data World
• A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts
• Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network
• Training generative neural networks via Maximum Mean Discrepancy optimization
• Learning in Implicit Generative Models
• Improved Techniques for Training Score-Based Generative Models
• Spatial postprocessing of ensemble forecasts for temperature using nonhomogeneous Gaussian regression
• Increasing the accuracy and resolution of precipitation forecasts using deep generative models
• Comparison of multivariate post-processing methods using global ECMWF ensemble forecasts
• Truncated generalized extreme value distribution based EMOS model for calibration of wind speed ensemble forecasts
• Probabilistic multivariate electricity price forecasting using implicit generative ensemble post-processing
• Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization
• Convolutional autoencoders for spatially-informed ensemble post-processing
• Evaluating forecasts for high-impact events using transformed kernel scores
• Multivariate Forecasting Evaluation: On Sensitive and Strictly Proper Scoring Rules

Cited by in corpus (7)

• A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Research
• Postprocessing of point predictions for probabilistic forecasting of day-ahead electricity prices: The benefits of using isotonic distributional regression
• Uncertainty Quantification of Wind Gust Predictions in the Northeast United States: An Evidential Neural Network and Explainable Artificial Intelligence Approach
• Machine learning-based probabilistic forecasting of solar irradiance in Chile
• Generative Machine Learning for Multivariate Angular Simulation
• A Composite-Loss Graph Neural Network for the Multivariate Post-Processing of Ensemble Weather Forecasts
• Enhancing multivariate post-processed visibility predictions utilizing CAMS forecasts