Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/9568
Title: | Inflow and sediment yield modeling of Vaigai reservoir using analytical and neural network approach |
Researcher: | Baskaran T |
Guide(s): | Nagan S |
Keywords: | Neural network |
Upload Date: | 27-Jun-2013 |
University: | Anna University |
Completed Date: | 2011 |
Abstract: | Many Indian reservoirs have lost their storage capacities because of sedimentation. Many of these reservoirs are losing capacity at the rate of0.2 1.0% annually. The sediment brought from upstream catchment through run off result in loss of capacity of reservoir. Thus there is an interaction between the runoff and sediment yield in a watershed. For a sustainable development through water resources planning and management, timely and accurate estimation of runoff and sediment yield through appropriate modeling are essential. This knowledge will allow estimating the probable lifespan of a reservoir and moreover to take proper measures against reservoir sedimentation. In this research, an ANN was developed and used to model the rainfall-runoff relationship in Vagai river basin. For this study, 41 years of annual rainfall records of 7 rain gauge stations located in Vaigai river basin was used. This model was developed in two phases namely training and testing phase. 70% of the available data are used in training phase remaining30% data were used for testing the model. From the result, it is clear that the predicted runoff fairly matches with the observed runoff. The results and comparative study indicate that artificial neural network method is more suitable to predict runoff when compared to analytical model. From this result, Vaigai reservoir will loose its purpose (70%loss)in the year 2108 according to analytical model whereas Vaigai reservoir will loose only 60% of its capacity as per the ANN model. Again the ANN model proves to be the best model for sediment deposition problems of reservoirs. Also, based on several performance indices, it was found that the ANN model estimated the volume of sediment retained in the reservoir with better accuracy and less effort as compared to conventional analysis. Hence, it is concluded from our research that ANN models are superior to analytical models in predicting run off and sediment yield of reservoirs. |
Pagination: | - |
URI: | http://hdl.handle.net/10603/9568 |
Appears in Departments: | Faculty of Civil Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | 52.33 kB | Adobe PDF | View/Open | |
02_certificate.pdf | 973.97 kB | Adobe PDF | View/Open | |
03_abstract.pdf | 24.08 kB | Adobe PDF | View/Open | |
04_acknowledgements.pdf | 20.6 kB | Adobe PDF | View/Open | |
05_table of contents.pdf | 24.49 kB | Adobe PDF | View/Open | |
06_list of tables.pdf | 20.51 kB | Adobe PDF | View/Open | |
07_list of figures.pdf | 21.65 kB | Adobe PDF | View/Open | |
08_symbols and abbreviations.pdf | 42.97 kB | Adobe PDF | View/Open | |
09_chapter 1.pdf | 114.88 kB | Adobe PDF | View/Open | |
10_chapter 2.pdf | 95.73 kB | Adobe PDF | View/Open | |
11_chapter 3.pdf | 407.46 kB | Adobe PDF | View/Open | |
12_chapter 4.pdf | 105.21 kB | Adobe PDF | View/Open | |
13_chapter 5.pdf | 204.57 kB | Adobe PDF | View/Open | |
14_chapter 6.pdf | 17.19 kB | Adobe PDF | View/Open | |
15_references.pdf | 33.31 kB | Adobe PDF | View/Open | |
16_appendix.pdf | 292.78 kB | Adobe PDF | View/Open | |
17_list of papers.pdf | 16 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: