Similarity-based semi-local estimation of EMOS models

Abstract

Weather forecasts are typically given in the form of forecast ensembles obtained from multiple runs of numerical weather prediction models with varying initial conditions and physics parameterizations. Such ensemble predictions tend to be biased and underdispersive and thus require statistical postprocessing. In the ensemble model output statistics (EMOS) approach, a probabilistic forecast is given by a single parametric distribution with parameters depending on the ensemble members. This article proposes two semi-local methods for estimating the EMOS coefficients where the training data for a specific observation station are augmented with corresponding forecast cases from stations with similar characteristics. Similarities between stations are determined using either distance functions or clustering based on various features of the climatology, forecast errors, ensemble predictions and locations of the observation stations. In a case study on wind speed over Europe with forecasts from the Grand Limited Area Model Ensemble Prediction System, the proposed similarity-based semi-local models show significant improvement in predictive performance compared to standard regional and local estimation methods. They further allow for estimating complex models without numerical stability issues and are computationally more efficient than local parameter estimation.

References in corpus (4)

• Log-normal distribution based EMOS models for probabilistic wind speed forecasting
• Probabilistic wind speed forecasting on a grid based on ensemble model output statistics
• Mixture EMOS model for calibrating ensemble forecasts of wind speed
• Customized training with an application to mass spectrometric imaging of cancer tissue

Cited by in corpus (16)

• Neural networks for post-processing ensemble weather forecasts
• Combining predictive distributions for statistical post-processing of ensemble forecasts
• Ensembles of Localised Models for Time Series Forecasting
• Generative machine learning methods for multivariate ensemble post-processing
• Machine learning methods for postprocessing ensemble forecasts of wind gusts: A systematic comparison
• Statistical post-processing of hydrological forecasts using Bayesian model averaging
• Truncated generalized extreme value distribution based EMOS model for calibration of wind speed ensemble forecasts
• Statistical post-processing of heat index ensemble forecasts: is there a royal road?
• Machine learning-based probabilistic forecasting of solar irradiance in Chile
• Calibration of wind speed ensemble forecasts for power generation
• Statistical post-processing of ensemble forecasts of temperature in Santiago de Chile
• Statistical post-processing of dual-resolution ensemble forecasts
• Statistical post-processing of visibility ensemble forecasts
• Parametric model for post-processing visibility ensemble forecasts
• Enhancing multivariate post-processed visibility predictions utilizing CAMS forecasts
• A Composite-Loss Graph Neural Network for the Multivariate Post-Processing of Ensemble Weather Forecasts