| Assessment of Dam Construction Effects on Downstream Water Quality Using Landsat 7 ETM+ Images (Case study: Taleghan dam) |
| Paper ID : 1295-SMPR |
| Authors: |
|
esmaeil norouzi1, Saeed Behzadi *2 1Department of Surveying Engineering, Faculty of Civil Engineering, ShahidRajaee University, Tehran, Iran 2Department of Surveying Engineering, Faculty of Civil Engineering |
| Abstract: |
| Water quality in the downstream of a hydroelectric dam may be affected by the structural design and operation. In order to sustain the ecosystem of the blocked rivers, the rivers health has to be kept safe. Therefore monitoring the water quality of downstream river is inevitable. Hydrological phenomena such as quantity of downstream water are affected by many environmental factors, which makes modeling difficult. On the other hand, the estimation of water quality for a target station can be difficult because of absence of local Hydrological data. In this regard, satellite imagery can play a unique role in modeling hydrological phenomena due to their significant advantages such as availability and their analysis. Therefore, addressing the improvement and expansion of machine learning methods and modeling algorithms using remote sensing data is inevitable. This study focuses on before and after dam construction trends water quality of the downstream river through Landsat Images. In this research, the ability of some machine modeling algorithms is studied to model data and water quality phenomena. We used two methods to prepare the database: PCA and standard deviation with correlation. The calculation of the Root Mean Squared Error (RMSE) indicated that the use of the PCA method has a better result in preparing and reducing the dimensions of large databases for all methods of machine learning. Results of the study indicate that the dam plays a significant role in regulating the water quality of its downstream. |
| Keywords: |
| Keywords: hydrological phenomena, Remote sensing, Machine learning, decision tree, PCA |
| Status : Conditional Accept (Poster) |
