Machine Learning-Based Evaporation Prediction and Kernel Function Analysis: A Case Study of the Boukourdane Dam, Algeria
Acta Scientiarum Polonorum. Formatio Circumiectus · 19.03.2026 · 25 (1) · 3-16
DOI: 10.15576/asp.fc/210976 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Scientiarum Polonorum. Formatio Circumiectus, online erschienen am 19.03.2026. Verfasst von Marouane BOUDJERDA und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Aim of the study The objective of this study is to evaluate the impact of three kernel functions—Pearson VII, radial basis function (RBF), and polynomial—on the predictive performance of Support Vector Regression (SVR) and Gaussian Process Regression (GPR) models. Material and methods Three machine learning models—Random Forest (RF), Support Vector Regression (SVR), and Gaussian Process Regression (GPR)—were applied, testing three kernels (Pearson VII, RBF, polynomial). The Pearson VII kernel’s novel use improves prediction under limited data. The dataset includes 240 observations over 20 years, with inputs: max/min air temperature, relative humidity, wind speed, and water temperature; output: evaporation. Results and conclusions Model performance was evaluated via Correlation Coefficient (CC), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). RF outperformed GPR and SVR across kernels, achieving MAE=1.01 mm, RMSE=1.29 mm, and CC=0.81 in testing. Moreover, the Pearson VII kernel delivered the highest accuracy within both GP and SVM frameworks. Sensitivity analysis highlighted relative humidity as the most influential factor in evaporation forecasting.
Zitieren
APA
BOUDJERDA, M., REHAMNIA, I., SIHAG, P., & Petroselli, A. (2026). Machine Learning-Based Evaporation Prediction and Kernel Function Analysis: A Case Study of the Boukourdane Dam, Algeria. Acta Scientiarum Polonorum. Formatio Circumiectus, 25(1), 3-16. https://doi.org/10.15576/asp.fc/210976
Vancouver
BOUDJERDA M, REHAMNIA I, SIHAG P, Petroselli A. Machine Learning-Based Evaporation Prediction and Kernel Function Analysis: A Case Study of the Boukourdane Dam, Algeria. Acta Scientiarum Polonorum. Formatio Circumiectus. 2026;25(1):3-16. doi:10.15576/asp.fc/210976
BibTeX
@article{BOUDJERDA2026,
author = {BOUDJERDA, Marouane and REHAMNIA, Issam and SIHAG, Parveen and Petroselli, Andrea},
title = {Machine Learning-Based Evaporation Prediction and Kernel Function Analysis: A Case Study of the Boukourdane Dam, Algeria},
journal = {Acta Scientiarum Polonorum. Formatio Circumiectus},
year = {2026},
volume = {25},
number = {1},
pages = {3--16},
doi = {10.15576/asp.fc/210976}
}
EUVIMED