Imagen de Portada

A Hybrid Extended Kalman Filter Based on Parametrized ANNs for the Improvement of the Forecasts of Numerical Weather and Wave Prediction Models

Guardado en:
Publicado en:Atmosphere vol. 15, no. 7 (2024), p. 828
Autor principal: Donas, Athanasios
Otros Autores: Galanis, George, Pytharoulis, Ioannis, Famelis, Ioannis Th
Publicado:
MDPI AG
Materias:
Greece
Mediterranean Sea
Wind speed
Kalman filters
Topography
Artificial neural networks
Weather
Neural networks
Air temperature
Wave predicting
Weather forecasting
Parameter uncertainty
Boundary conditions
Prediction models
Case studies
Covariance matrix
Systematic errors
Simulation
Parameterization
Parameter estimation
Radial basis function
Numerical models
Mathematical models
Electromagnetic wave filters
Wave height
Land use
Error reduction
Significant wave height
Algorithms
Hybrid systems
Extended Kalman filter
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:A hybrid optimization filter for weather and wave numerical models is proposed and tested in this study. Parametrized Artificial Neural Networks are utilized in conjunction with Extended Kalman Filters to provide a novel postprocess strategy for 10 m wind speed, 2 m air temperature, and significant wave height simulations. The innovation of the developed model is the implementation of Feedforward Neural Networks and Radial Basis Function Neural Networks as estimators of an exogenous parameter that adjusts the covariance matrices of the Extended Kalman Filter process. This hybrid system is evaluated through a time window process leading to promising results, thus enabling a decrease in systematic errors alongside the restriction of the error variability and the corresponding forecast uncertainty. The obtained results showed that the average reduction of the systematic error exceeded 75%, while the corresponding nonsystematic part of that error decreased by 35%.
ISSN:2073-4433
DOI:10.3390/atmos15070828
Fuente:Publicly Available Content Database