A Dual Filter Based on Radial Basis Function Neural Networks and Kalman Filters with Application to Numerical Wave Prediction Models

The aim of this study is to introduce and evaluate a dual filter that combines Radial Basis Function neural networks and Kalman filters to enhance the accuracy of numerical wave prediction models. Unlike the existing methods, which focus solely on systematic errors, the proposed framework concurrent...

Full description

Saved in:
Bibliographic Details
Main Authors: Athanasios Donas, Ioannis Kordatos, Alex Alexandridis, George Galanis, Ioannis Th. Famelis
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/24/8006
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037249214775296
author Athanasios Donas
Ioannis Kordatos
Alex Alexandridis
George Galanis
Ioannis Th. Famelis
author_facet Athanasios Donas
Ioannis Kordatos
Alex Alexandridis
George Galanis
Ioannis Th. Famelis
author_sort Athanasios Donas
collection DOAJ
description The aim of this study is to introduce and evaluate a dual filter that combines Radial Basis Function neural networks and Kalman filters to enhance the accuracy of numerical wave prediction models. Unlike the existing methods, which focus solely on systematic errors, the proposed framework concurrently targets both systematic and non-systematic parts of forecast errors, significantly reducing the bias and variability in significant wave height predictions. The produced filter is self-adaptive, identifying optimal Radial Basis Function network configurations through an automated process involving various network parameters tuning. The produced computational system is assessed using a time-window procedure applied across divergent time periods and regions in the Aegean Sea and the Pacific Ocean. The results reveal a consistent performance, outperforming classic Kalman filters with an average reduction of 53% in bias and 28% in RMSE, underlining the dual filter’s potential as a robust post-processing tool for environmental simulations.
format Article
id doaj-art-1c728aedd38c4bfaa6ae720b1aee86df
institution DOAJ
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-1c728aedd38c4bfaa6ae720b1aee86df2025-08-20T02:56:55ZengMDPI AGSensors1424-82202024-12-012424800610.3390/s24248006A Dual Filter Based on Radial Basis Function Neural Networks and Kalman Filters with Application to Numerical Wave Prediction ModelsAthanasios Donas0Ioannis Kordatos1Alex Alexandridis2George Galanis3Ioannis Th. Famelis4Department of Electrical and Electronic Engineering, University of West Attica, Ancient Olive Grove Campus, 250, Thivon Ave., Egaleo, 12241 Athens, GreeceDepartment of Electrical and Electronic Engineering, University of West Attica, Ancient Olive Grove Campus, 250, Thivon Ave., Egaleo, 12241 Athens, GreeceDepartment of Electrical and Electronic Engineering, University of West Attica, Ancient Olive Grove Campus, 250, Thivon Ave., Egaleo, 12241 Athens, GreeceHellenic Naval Academy, Hatzikiriakion, 18539 Piraeus, GreeceDepartment of Electrical and Electronic Engineering, University of West Attica, Ancient Olive Grove Campus, 250, Thivon Ave., Egaleo, 12241 Athens, GreeceThe aim of this study is to introduce and evaluate a dual filter that combines Radial Basis Function neural networks and Kalman filters to enhance the accuracy of numerical wave prediction models. Unlike the existing methods, which focus solely on systematic errors, the proposed framework concurrently targets both systematic and non-systematic parts of forecast errors, significantly reducing the bias and variability in significant wave height predictions. The produced filter is self-adaptive, identifying optimal Radial Basis Function network configurations through an automated process involving various network parameters tuning. The produced computational system is assessed using a time-window procedure applied across divergent time periods and regions in the Aegean Sea and the Pacific Ocean. The results reveal a consistent performance, outperforming classic Kalman filters with an average reduction of 53% in bias and 28% in RMSE, underlining the dual filter’s potential as a robust post-processing tool for environmental simulations.https://www.mdpi.com/1424-8220/24/24/8006Kalman filterspost-process algorithmsradial basis function neural networkssignificant wave heightWAM
spellingShingle Athanasios Donas
Ioannis Kordatos
Alex Alexandridis
George Galanis
Ioannis Th. Famelis
A Dual Filter Based on Radial Basis Function Neural Networks and Kalman Filters with Application to Numerical Wave Prediction Models
Sensors
Kalman filters
post-process algorithms
radial basis function neural networks
significant wave height
WAM
title A Dual Filter Based on Radial Basis Function Neural Networks and Kalman Filters with Application to Numerical Wave Prediction Models
title_full A Dual Filter Based on Radial Basis Function Neural Networks and Kalman Filters with Application to Numerical Wave Prediction Models
title_fullStr A Dual Filter Based on Radial Basis Function Neural Networks and Kalman Filters with Application to Numerical Wave Prediction Models
title_full_unstemmed A Dual Filter Based on Radial Basis Function Neural Networks and Kalman Filters with Application to Numerical Wave Prediction Models
title_short A Dual Filter Based on Radial Basis Function Neural Networks and Kalman Filters with Application to Numerical Wave Prediction Models
title_sort dual filter based on radial basis function neural networks and kalman filters with application to numerical wave prediction models
topic Kalman filters
post-process algorithms
radial basis function neural networks
significant wave height
WAM
url https://www.mdpi.com/1424-8220/24/24/8006
work_keys_str_mv AT athanasiosdonas adualfilterbasedonradialbasisfunctionneuralnetworksandkalmanfilterswithapplicationtonumericalwavepredictionmodels
AT ioanniskordatos adualfilterbasedonradialbasisfunctionneuralnetworksandkalmanfilterswithapplicationtonumericalwavepredictionmodels
AT alexalexandridis adualfilterbasedonradialbasisfunctionneuralnetworksandkalmanfilterswithapplicationtonumericalwavepredictionmodels
AT georgegalanis adualfilterbasedonradialbasisfunctionneuralnetworksandkalmanfilterswithapplicationtonumericalwavepredictionmodels
AT ioannisthfamelis adualfilterbasedonradialbasisfunctionneuralnetworksandkalmanfilterswithapplicationtonumericalwavepredictionmodels
AT athanasiosdonas dualfilterbasedonradialbasisfunctionneuralnetworksandkalmanfilterswithapplicationtonumericalwavepredictionmodels
AT ioanniskordatos dualfilterbasedonradialbasisfunctionneuralnetworksandkalmanfilterswithapplicationtonumericalwavepredictionmodels
AT alexalexandridis dualfilterbasedonradialbasisfunctionneuralnetworksandkalmanfilterswithapplicationtonumericalwavepredictionmodels
AT georgegalanis dualfilterbasedonradialbasisfunctionneuralnetworksandkalmanfilterswithapplicationtonumericalwavepredictionmodels
AT ioannisthfamelis dualfilterbasedonradialbasisfunctionneuralnetworksandkalmanfilterswithapplicationtonumericalwavepredictionmodels