Enhancing Streamflow Prediction Accuracy: A Comprehensive Analysis of Hybrid Neural Network Models with Runge–Kutta with Aquila Optimizer

Abstract This study investigates the efficacy of hybrid artificial neural network (ANN) methods, incorporating metaheuristic algorithms such as particle swarm optimization (PSO), genetic algorithm (GA), gray wolf optimizer (GWO), Aquila optimizer (AO), Runge–Kutta (RUN), and the novel ANN-based Rung...

Full description

Saved in:
Bibliographic Details
Main Authors: Rana Muhammad Adnan, Wang Mo, Ahmed A. Ewees, Salim Heddam, Ozgur Kisi, Mohammad Zounemat-Kermani
Format: Article
Language:English
Published: Springer 2024-11-01
Series:International Journal of Computational Intelligence Systems
Subjects:
Online Access:https://doi.org/10.1007/s44196-024-00699-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846147432323219456
author Rana Muhammad Adnan
Wang Mo
Ahmed A. Ewees
Salim Heddam
Ozgur Kisi
Mohammad Zounemat-Kermani
author_facet Rana Muhammad Adnan
Wang Mo
Ahmed A. Ewees
Salim Heddam
Ozgur Kisi
Mohammad Zounemat-Kermani
author_sort Rana Muhammad Adnan
collection DOAJ
description Abstract This study investigates the efficacy of hybrid artificial neural network (ANN) methods, incorporating metaheuristic algorithms such as particle swarm optimization (PSO), genetic algorithm (GA), gray wolf optimizer (GWO), Aquila optimizer (AO), Runge–Kutta (RUN), and the novel ANN-based Runge–Kutta with Aquila optimizer (LSTM-RUNAO). The key novelty of this research lies in the developing and applying the LSTM-RUNAO model, which combines Runge–Kutta and Aquila optimizer to enhance streamflow prediction accuracy. The models’ performance is compared against the conventional ANN method, analyzing monthly streamflow prediction across three data split scenarios (50–50%, 60–40%, and 75–25%). Results show that the LSTM-RUNAO model outperformed conventional ANN methods, achieving a 28.7% reduction in root mean square error (RMSE) and a 20.3% reduction in mean absolute error (MAE) compared to standard ANN models. In addition, the model yielded a Nash–Sutcliffe Efficiency (NSE) improvement of 12.4% and an R-squared value increase of 7.8%. The study advocates for the 75–25% train-test data splitting scenario for optimal performance in data-driven methodologies. Furthermore, it elucidates the nuanced influence of input variables on prediction accuracy, emphasizing the importance of thoughtful consideration during model development. In summary, this research contributes valuable insights and introduces an innovative hybrid model to enhance the reliability of streamflow prediction models for practical applications.
format Article
id doaj-art-a8fd908529d24f74ab02dce8283879b5
institution Kabale University
issn 1875-6883
language English
publishDate 2024-11-01
publisher Springer
record_format Article
series International Journal of Computational Intelligence Systems
spelling doaj-art-a8fd908529d24f74ab02dce8283879b52024-12-01T12:44:01ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832024-11-0117112310.1007/s44196-024-00699-yEnhancing Streamflow Prediction Accuracy: A Comprehensive Analysis of Hybrid Neural Network Models with Runge–Kutta with Aquila OptimizerRana Muhammad Adnan0Wang Mo1Ahmed A. Ewees2Salim Heddam3Ozgur Kisi4Mohammad Zounemat-Kermani5College of Architecture and Urban Planning, Guangzhou UniversityCollege of Architecture and Urban Planning, Guangzhou UniversityDepartment of Computer, Damietta UniversityFaculty of Science, Agronomy Department, University of SkikdaDepartment of Civil Engineering, Lübeck University of Applied SciencesDepartment of Water Engineering, Shahid Bahonar University of KermanAbstract This study investigates the efficacy of hybrid artificial neural network (ANN) methods, incorporating metaheuristic algorithms such as particle swarm optimization (PSO), genetic algorithm (GA), gray wolf optimizer (GWO), Aquila optimizer (AO), Runge–Kutta (RUN), and the novel ANN-based Runge–Kutta with Aquila optimizer (LSTM-RUNAO). The key novelty of this research lies in the developing and applying the LSTM-RUNAO model, which combines Runge–Kutta and Aquila optimizer to enhance streamflow prediction accuracy. The models’ performance is compared against the conventional ANN method, analyzing monthly streamflow prediction across three data split scenarios (50–50%, 60–40%, and 75–25%). Results show that the LSTM-RUNAO model outperformed conventional ANN methods, achieving a 28.7% reduction in root mean square error (RMSE) and a 20.3% reduction in mean absolute error (MAE) compared to standard ANN models. In addition, the model yielded a Nash–Sutcliffe Efficiency (NSE) improvement of 12.4% and an R-squared value increase of 7.8%. The study advocates for the 75–25% train-test data splitting scenario for optimal performance in data-driven methodologies. Furthermore, it elucidates the nuanced influence of input variables on prediction accuracy, emphasizing the importance of thoughtful consideration during model development. In summary, this research contributes valuable insights and introduces an innovative hybrid model to enhance the reliability of streamflow prediction models for practical applications.https://doi.org/10.1007/s44196-024-00699-yStreamflow predictionNeural networksData splittingRunge–Kutta with Aquila optimizer
spellingShingle Rana Muhammad Adnan
Wang Mo
Ahmed A. Ewees
Salim Heddam
Ozgur Kisi
Mohammad Zounemat-Kermani
Enhancing Streamflow Prediction Accuracy: A Comprehensive Analysis of Hybrid Neural Network Models with Runge–Kutta with Aquila Optimizer
International Journal of Computational Intelligence Systems
Streamflow prediction
Neural networks
Data splitting
Runge–Kutta with Aquila optimizer
title Enhancing Streamflow Prediction Accuracy: A Comprehensive Analysis of Hybrid Neural Network Models with Runge–Kutta with Aquila Optimizer
title_full Enhancing Streamflow Prediction Accuracy: A Comprehensive Analysis of Hybrid Neural Network Models with Runge–Kutta with Aquila Optimizer
title_fullStr Enhancing Streamflow Prediction Accuracy: A Comprehensive Analysis of Hybrid Neural Network Models with Runge–Kutta with Aquila Optimizer
title_full_unstemmed Enhancing Streamflow Prediction Accuracy: A Comprehensive Analysis of Hybrid Neural Network Models with Runge–Kutta with Aquila Optimizer
title_short Enhancing Streamflow Prediction Accuracy: A Comprehensive Analysis of Hybrid Neural Network Models with Runge–Kutta with Aquila Optimizer
title_sort enhancing streamflow prediction accuracy a comprehensive analysis of hybrid neural network models with runge kutta with aquila optimizer
topic Streamflow prediction
Neural networks
Data splitting
Runge–Kutta with Aquila optimizer
url https://doi.org/10.1007/s44196-024-00699-y
work_keys_str_mv AT ranamuhammadadnan enhancingstreamflowpredictionaccuracyacomprehensiveanalysisofhybridneuralnetworkmodelswithrungekuttawithaquilaoptimizer
AT wangmo enhancingstreamflowpredictionaccuracyacomprehensiveanalysisofhybridneuralnetworkmodelswithrungekuttawithaquilaoptimizer
AT ahmedaewees enhancingstreamflowpredictionaccuracyacomprehensiveanalysisofhybridneuralnetworkmodelswithrungekuttawithaquilaoptimizer
AT salimheddam enhancingstreamflowpredictionaccuracyacomprehensiveanalysisofhybridneuralnetworkmodelswithrungekuttawithaquilaoptimizer
AT ozgurkisi enhancingstreamflowpredictionaccuracyacomprehensiveanalysisofhybridneuralnetworkmodelswithrungekuttawithaquilaoptimizer
AT mohammadzounematkermani enhancingstreamflowpredictionaccuracyacomprehensiveanalysisofhybridneuralnetworkmodelswithrungekuttawithaquilaoptimizer