Ahmadi, S. H. (2018) Perdiction of Quantitative and Qualitative Parameters of Shawor River Using Artificial Intelligence Methods. Masters thesis, university of zabol.
|
Text
Perdiction of Quantitative and.pdf Download (192kB) | Preview |
Abstract
Freshwater is one of the main factors for sustainable development and maintaining the health of societies, which, in addition to quantitative, qualitative status is also very important. Rivers are considered as one of the main sources of fresh water for various uses, such as drinking water, agriculture and the environment, as the basis for the sustainable development of human societies in today's world. The prediction of quantitative and qualitative water parameters plays a decisive role in the quality management and environmental policy of water resources. Due to the nonlinearity of some physical processes and uncertainty in the characteristics, one can use the modeling technique to simulate and predict uncertain and nonlinear processes. In this research, artificial intelligence techniques including neural networks and neuro-fuzzy adaptive inference system were used to estimate quantitative and qualitative parameters of shawor river such as (Total Dissolved solids (TDS), discharge (Q), Electrical condctivity (EC) and sodium adsorption ratio (SAR). In this research, information on the quantitative and qualitative parameters of Shawor River measured at Shawor station and the 31 year common period will be used between 1365 and 1395. Available data are divided into two parts: calibration data and test data. Calibration is performed by 85% of the data (for 70% training and 15% validation), and the performance of the methods is assessed using 15% of the remaining data. In order to compare the measured values with the predicted values, the normalized root mean square error or NRMSE, Nash-sutcliff coefficient and coefficient of defermintion were used. The results show that in some cases, the neural network has a relative superiority to the neuro-fuzzy inference system model.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Artificial Neural Networks, Neuro-Fuzzy Adaptive Inference System,TDS, EC, SAR |
| Subjects: | T Technology > TC Hydraulic engineering. Ocean engineering |
| Depositing User: | Mrs najmeh khajeh |
| Date Deposited: | 08 Dec 2018 05:17 |
| Last Modified: | 09 Mar 2019 09:38 |
| URI: | http://eprints.uoz.ac.ir/id/eprint/2322 |
Actions (login required)
 |
View Item |
