Loading...

Modelling and Prediction of Water Quality of Dam Reservoir Using CE-QUAL-W2 Model and Machine Learning Methods (Case Study: Shahr Bijar Dam)

Ebrahimi, Abolfazl | 2022

140 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55346 (09)
  4. University: Sharif University of Technology
  5. Department: Civil Engineering
  6. Advisor(s): Shamsai, Abolfazl; Ghaemian, Mohsen
  7. Abstract:
  8. Dams are constructed for various purposes, including flood control, drinking water supply, agriculture irrigation, electricity generation, etc. The dam converts the river's natural and dynamic flow into a stagnant artificial lake where humans control the outflow of water, reducing the velocity of water movement and increasing residence time, followed by the entry and accumulation of nutrients in the reservoir, resulting in phenomena such as thermal stratification and eutrophication. Due to the changing climatic conditions of Iran and sudden droughts and wet periods, the need to monitor the water level of dam reservoirs and their water quality to keep them in the best operational condition in line with the objectives set for them is inevitable. The objective of this study is to predict reservoir water level and qualitative parameters such as dissolved oxygen (DO), phosphate (PO4), ammonium (NH4) and total soluble solids (TDS) using machine learning algorithms, namely multiple linear regression and Support Vector Regression, as well as modeling temperature and water quality and selecting the best intake gate level in different seasons in terms of surface water quality index of Iran in Shar Bijar dam of Guilan province using the CE-QUAL-W2 model. The results demonstrated that the algorithms utilized in this study were capable of predicting reservoir water level and water quality parameters with reasonable accuracy. The MLR algorithm, however, outperformed the SVR algorithm. The MLR method has a coefficient of determination (R2) of 0.988 for predicting reservoir level and 0.965, 0.905, 0.888, and 0.935 for predicting dissolved oxygen, phosphate, ammonium, and total solids in dam reservoirs, respectively. The simulation results also demonstrated that the quality index in all three intake gates is equal in winter. However, in fall, spring, and summer, the third intake gate which has an index of 83.3, 85.5, and 79.8 provides higher quality water to consumers
  9. Keywords:
  10. Artificial Intelligence ; Machine Learning ; Water Quality ; Eutrophication ; Water Quality Modeling ; Thermal Stratification

 Digital Object List

 Bookmark

No TOC