DONATE

IAHR Document Library


« Back to Library Homepage « Book of Abstracts of the 8th IAHR Europe Congress (Lisbon, 2...

Optimization of Supervised Learning Chain Models for Monthly Flow Prediction

Author(s): Jadran Berbic; Eva Ocvirk

Linked Author(s): Jadran Berbić

Keywords: No Keywords

Abstract: The objective of the work is to improve modeling procedure of mean monthly flows for the purpose of long-term prediction. After the treatment and choice of independent variables, genetic algorithm has been applied to select optimal model hyperparameters of supervised learning models - artificial neural network (ANN), support vector machine (SVM), histogram gradient boosting regressor (HGBR) and elastic net (EN). Models were applied in chain modeling procedure in a manner of providing mean monthly flow at Vinalic (river Cetina, Croatia) for six (6) months per every sample of dataset.

DOI:

Year: 2024

Copyright © 2025 International Association for Hydro-Environment Engineering and Research. All rights reserved. | Terms and Conditions