Journal of Wetland Ecobiology
Volume 17, Issue 3 (Autumn 2025)
2025, 17(3): 14-30 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Rostami R, Fathian H. Prediction of Evaporation Losses from Boukan Dam Reservoir Using Adaptive Neuro-Fuzzy Inference System. Wetland Ecobiology 2025; 17 (3) : 2
URL: http://jweb.ahvaz.iau.ir/article-1-1122-en.html
URL: http://jweb.ahvaz.iau.ir/article-1-1122-en.html
Islamic Azad University
Abstract: (276 Views)
Evaporation from dam reservoir surfaces is considered a key parameter in hydrology and water resource management. The complexity of nonlinear relationships among meteorological factors limits the accuracy of classical evaporation estimation methods. In this research, a Neuro-Fuzzy Inference System was employed as a novel approach for predicting evaporation from the Boukan Dam reservoir in West Azerbaijan Province, Iran. Monthly meteorological data from 2008-2023, including air temperature, relative humidity, and precipitation, were used as model inputs, while monthly evaporation was considered the output. Regression analysis was used to select the optimal combination of input parameters, with eight different combinations being tested. The model performed best with maximum temperature as input. The Trimf (triangular) membership function yielded the best results. Furthermore, 100 training epochs performed better than other epoch numbers. In the best scenario, the correlation coefficient between observed and predicted data was 0.927. These findings demonstrate the high capability of the neuro-fuzzy system in predicting evaporation from the Boukan Dam reservoir and present a more accurate approach compared to traditional methods.
Article number: 2
Keywords: Monthly Evaporation Prediction, Boukan Dam, Neuro-Fuzzy Inference System, Maximum Temperature.
Type of Study: Applicable |
Subject:
Special
Received: 2025/12/31 | Accepted: 2026/01/31 | Published: 2026/01/31
Received: 2025/12/31 | Accepted: 2026/01/31 | Published: 2026/01/31
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |