A Modified Kalman Filter Based on Radial Basis Function Neural Networks for the Improvement of Numerical Weather Prediction Models

Zapisane w:
Opis bibliograficzny
Wydane w:Atmosphere vol. 16, no. 3 (2025), p. 248
1. autor: Donas, Athanasios
Kolejni autorzy: Galanis, George, Pytharoulis, Ioannis, Famelis, Ioannis Th
Wydane:
MDPI AG
Hasła przedmiotowe:
Dostęp online:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etykiety: Dodaj etykietę
Nie ma etykietki, Dołącz pierwszą etykiete!

MARC

LEADER 00000nab a2200000uu 4500
001 3181383537
003 UK-CbPIL
022 |a 2073-4433 
024 7 |a 10.3390/atmos16030248  |2 doi 
035 |a 3181383537 
045 2 |b d20250101  |b d20251231 
084 |a 231428  |2 nlm 
100 1 |a Donas, Athanasios  |u microSENSES Laboratory, Department of Electrical and Electronics Engineering, University of West Attica, Ancient Olive Grove Campus, 250, Thivon Ave., Egaleo, 12241 Athens, Greece; <email>adonas@uniwa.gr</email> 
245 1 |a A Modified Kalman Filter Based on Radial Basis Function Neural Networks for the Improvement of Numerical Weather Prediction Models 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a This study introduces a novel enhancement to the Kalman filter algorithm by integrating it with Radial Basis Function neural networks to improve numerical weather prediction models. Traditional Kalman filters frequently underperform when used by dynamical systems due to their reliance on fixed covariance matrices, resulting in inaccuracies and forecast uncertainty. The proposed modified Kalman filter utilizes Radial Basis Function neural networks to estimate covariance matrices adaptively during the filtering process. This self-adaptive computational system enables the simultaneous targeting of the systematic and the remaining non-systematic parts of the forecast error, producing an innovative and efficient post-process strategy. The suggested methodology is evaluated on predictions of 10-meter wind speed and 2-meter air temperature obtained from the Weather Research and Forecasting model for observation stations in northern Greece. The derived results demonstrate a significant reduction in systematic error, as the bias decreased by up to 88% for 10-meter wind speed and 58% for 2-meter air temperature. Additionally, the forecast variability was successfully mitigated, with the RMSE reduced by 39% and 40%, respectively. Compared to the traditional Kalman filter, which exhibited increased RMSE in several cases and failed to control forecast uncertainty, the proposed approach consistently outperformed by providing stable and reliable predictions across all examined scenarios. These improvements validate the robustness of the method in comparison to conventional techniques, highlighting its potential to produce reliable and stable predictions for environmental applications. 
610 4 |a US Geological Survey 
651 4 |a Greece 
651 4 |a Mediterranean Sea 
653 |a Weather forecasting 
653 |a Wind speed 
653 |a Weather 
653 |a Neural networks 
653 |a Air temperature 
653 |a Forecast errors 
653 |a Numerical weather forecasting 
653 |a Uncertainty 
653 |a Prediction models 
653 |a Kalman filters 
653 |a Systematic errors 
653 |a Adaptive systems 
653 |a Precipitation 
653 |a Forecasting models 
653 |a Algorithms 
653 |a Error reduction 
653 |a Deep learning 
653 |a Boundary conditions 
653 |a Bias 
653 |a Covariance matrix 
653 |a Machine learning 
653 |a Radial basis function 
653 |a Temperature 
653 |a Climate science 
653 |a Rain 
700 1 |a Galanis, George  |u Mathematical Modeling and Applications Laboratory, Hellenic Naval Academy, Hatzikiriakion, 18539 Piraeus, Greece; <email>ggalanis@hna.gr</email> 
700 1 |a Pytharoulis, Ioannis  |u Department of Meteorology and Climatology, School of Geology, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece; <email>pyth@geo.auth.gr</email> 
700 1 |a Famelis, Ioannis Th  |u microSENSES Laboratory, Department of Electrical and Electronics Engineering, University of West Attica, Ancient Olive Grove Campus, 250, Thivon Ave., Egaleo, 12241 Athens, Greece; <email>adonas@uniwa.gr</email> 
773 0 |t Atmosphere  |g vol. 16, no. 3 (2025), p. 248 
786 0 |d ProQuest  |t Publicly Available Content Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3181383537/abstract/embedded/H09TXR3UUZB2ISDL?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3181383537/fulltextwithgraphics/embedded/H09TXR3UUZB2ISDL?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3181383537/fulltextPDF/embedded/H09TXR3UUZB2ISDL?source=fedsrch