Ratul et al. (2026) Performance Evaluation of ANN and LSTM Combined with Orangutan Algorithm for Enhanced Prediction of Streamflow

Identification

• Journal: Lecture notes in civil engineering
• Year: 2026
• Date: 2026-01-01
• Authors: Md. Jobayer Parvez Ratul, Sajal Kumar Adhikary, Usmi Akter, M. Mubtasim Fuad Dip, Hrithik Nath
• DOI: 10.1007/978-3-032-18708-6_12

Research Groups

• Department of Civil Engineering, Khulna University of Engineering & Technology, Khulna, Bangladesh
• Department of Civil and Environmental Engineering, University of Missouri, Columbia, MO, USA

Short Summary

This study develops and evaluates hybrid machine learning (ML) and deep learning (DL) models, integrating Artificial Neural Networks (ANN) and Long Short-Term Memory (LSTM) with the Orangutan Optimization Algorithm (OOA), to enhance streamflow prediction accuracy. The research demonstrates that these OOA-optimized hybrid models significantly outperform standalone ANN and LSTM models, with OOA-ANN showing the best performance.

Objective

• To enhance the predictive accuracy of Artificial Neural Networks (ANN) and Long Short-Term Memory (LSTM) models for streamflow prediction by integrating them with the nature-inspired Orangutan Optimization Algorithm (OOA).

Study Configuration

• Spatial Scale: Gorai River, specifically at the Gorai Railway Bridge station in Bangladesh.
• Temporal Scale: Daily streamflow time series data.

Methodology and Data

• Models used: Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), Orangutan Optimization Algorithm (OOA). Hybrid models: OOA-ANN and OOA-LSTM.
• Data sources: Daily streamflow time series data from the Gorai Railway Bridge station.

Main Results

• Hybrid OOA-ANN and OOA-LSTM models demonstrated superior streamflow prediction performance compared to standalone ANN and LSTM models.
• The hybrid OOA-ANN model specifically outperformed all other developed models in the study.
• Performance was evaluated using Normalized Root Mean Squared Error (NRMSE), Kling-Gupta Efficiency (KGE), Mean Absolute Error (MAE), and coefficient of determination (R) during both training and testing phases.

Contributions

• Introduction and application of the novel Orangutan Optimization Algorithm (OOA) to optimize ANN and LSTM models for streamflow prediction, addressing limitations of manual tuning in conventional ML/DL models.
• Development and validation of hybrid OOA-ANN and OOA-LSTM models, proving their viability for enhanced streamflow prediction.
• Quantitative demonstration of improved predictive accuracy of hybrid models over standalone counterparts using multiple statistical metrics.

Funding

• Not explicitly stated in the provided paper text.

Citation

@article{Ratul2026Performance,
  author = {Ratul, Md. Jobayer Parvez and Adhikary, Sajal Kumar and Akter, Usmi and Dip, M. Mubtasim Fuad and Nath, Hrithik},
  title = {Performance Evaluation of ANN and LSTM Combined with Orangutan Algorithm for Enhanced Prediction of Streamflow},
  journal = {Lecture notes in civil engineering},
  year = {2026},
  doi = {10.1007/978-3-032-18708-6_12},
  url = {https://doi.org/10.1007/978-3-032-18708-6_12}
}