Anzeige
Erschienen in:
2016 | Supplement | Buchkapitel
Tuning Parameters of Ensemble Prediction System and Optimization with Differential Evolution Approach
verfasst von : Vladimir Shemyakin, Heikki Haario
Erschienen in: Progress in Industrial Mathematics at ECMI 2014
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Ensemble Prediction System (EPS) is the approach used in present day weather predictions to estimate the uncertainty of predictions. Along with the main prediction an ensemble of simulations is launched with perturbed initial values. Recently, the EPS with simultaneous parameter estimation approach (EPPES) has been proposed to tune model parameters online, without additional computational costs, by perturbing the parameter values and monitoring the respective performances. The key point of EPPES is the estimation of the parameter covariance by sequentially updating the covariance as hyperparameters by aid of importance weights. Here, we study the Differential Evolution (DE) optimization approach as a new way to solve the problem as a stochastic optimization task. We show that the convergence is improved using DE, especially in case when initial values of model parameters are far enough from the true ones.