Development of a new technique Dam Gates Opening Scheme based on Whale Optimization Algorithm with Long Short Term Memory (WOA-LSTM)

Salih, A, Zhang, Q ORCID: 0000-0002-0651-469X, Raschella, A ORCID: 0000-0002-1626-8947, Mohammed, A ORCID: 0009-0003-8426-6964, Abdullah, BM ORCID: 0000-0002-1281-148X, Aldhaibani, OA ORCID: 0000-0003-0235-2862, Maheshwari, MK and Qiu, Y ORCID: 0000-0003-0266-1294 (2026) Development of a new technique Dam Gates Opening Scheme based on Whale Optimization Algorithm with Long Short Term Memory (WOA-LSTM). In: 2026 1st International Conference on Emerging Trends in Advancements and Applications of Computational Intelligence Techniques (ETAACT) . pp. 1-6. (2026 1st International Conference on Emerging Trends in Advancements and Applications of Computational Intelligence Techniques (ETAACT), 10th Apr- 11th Apr 2026, Bhubaneswar, India).

Preview

Text 2026155972.pdf - Accepted Version Download (1MB) | Preview

Abstract

The implementation, operation, and management of dams are crucial for the timely supply of water. This study aims to improve water management in Haditha Dam, Iraq, using the Whale Optimization Algorithm (WOA). To address the challenge of uncertainty in Long Short-Term Memory (LSTM) model predictions and enhance the accuracy of inflow and outflow forecasts, we propose a novel WOA-LSTM model that by designed a custom target function that combines reducing the deviation of the reservoir level from the target, strict penalties for exceeding safe limits, restrictions on the rate of change of the gates opening [ramprate ≤ 50m3/s/day]. This ensures a minimum environmental flow (150m3/s). The results demonstrate that, through continuous tuning of hyperparameters, WOA effectively optimizes the LSTM predictions, improving forecasting accuracy. Compared with other neural network models, the WOA-LSTM approach reduces Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) while increasing the coefficient of determination (R2). Furthermore, a separate WOA optimization is applied to achieve optimal dam operation by adjusting gate openings according to the predicted inflow, maintaining reservoir levels effectively.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	© 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Subjects:	Q Science > QA Mathematics > QA76 Computer software T Technology > TA Engineering (General). Civil engineering (General)
Divisions:	Civil Engineering and Built Environment Computer Science and Mathematics Engineering
Publisher:	IEEE
Date of acceptance:	10 January 2026
Date of first compliant Open Access:	4 June 2026
Date Deposited:	04 Jun 2026 14:01
Last Modified:	04 Jun 2026 14:01
DOI or ID number:	10.1109/etaact69135.2026.11541768
URI:	https://researchonline.ljmu.ac.uk/id/eprint/28731

View Item