DocumentCode
1735128
Title
Data Analysis, Discharge Classifications, and Predictions of Hydrological Parameters for the Management of Rawal Dam in Pakistan
Author
Ali, Mohamed ; Qamar, Ali Mustafa ; Ali, Borhanuddin
Author_Institution
Sch. of Electr. Eng. & Comput. Sci., Nat. Univ. of Sci. & Technol., Islamabad, Pakistan
Volume
1
fYear
2013
Firstpage
382
Lastpage
385
Abstract
Rawal Dam is a strategic asset for the twin cities of Islamabad and Rawalpindi in Pakistan being the main source of drinking as well as agricultural water supplies. The low-lying areas of the reservoir are being affected by reservoir storage and spillways´ discharge. For the effective management, modeling techniques would not only be cost effective but also help the water managers in predicting the future scenarios of water discharge. In this paper, last twelve years (2001-2012) trends of hydrological parameters, attribute selection, discharge classification in terms of spillway gates opening, and prediction methods for the forecasting of hydrological parameters at the Rawal Dam is presented. Our research suggests that August is a crucial month for inflow and spillways discharge. Similarly, September and October are critical for level and total storage capacity which are critical parameters for discharge management. J48 tree classification technique gave better results for discharge management. Finally, in order to forecast the critical parameters, the improved SVM technique for water level and the regression technique for storage capacity has been found to be more accurate.
Keywords
agriculture; dams; data analysis; hydrology; reservoirs; support vector machines; trees (mathematics); Islamabad; J48 tree classification technique; Pakistan; Rawal dam; Rawalpindi; SVM technique; agricultural water supplies; attribute selection; data analysis; discharge classifications; hydrological parameters; reservoir storage; spillways discharge; water discharge; Forecasting; Logic gates; Market research; Mathematical model; Predictive models; Support vector machines; Time series analysis; Classification; data extrapolation; regression; time series model; water management; water storage;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning and Applications (ICMLA), 2013 12th International Conference on
Conference_Location
Miami, FL
Type
conf
DOI
10.1109/ICMLA.2013.78
Filename
6784648
Link To Document