- English
- فارسی
Safavi, H.R., Esmikhani, M. (2013). Conjunctive use of surface water and groundwater: Application of support vector machines (SVMs) and genetic algorithms. J. of Water Resources Management, Vol. 27, No. 7, pp. 2623-2644.
Conjunctive Use of Surface Water and Groundwater: Application of Support Vector Machines (SVMs) and Genetic Algorithms
Hamid R. Safavi1, and Mahdieh Esmikhani2
- Associate Professor, Dept. of Civil Engineering, Isfahan University of Technology, Isfahan, Iran.
E-mail: hasafavi@cc.iut.ac.ir
- Graduate Student, Dept. of Civil Engineering, Isfahan University of Technology, Isfahan, Iran.
E-mail: esmikhani@cv.iut.ac.ir
Abstract:
Combined simulation-optimization models have been widely used to address the management of water resources issues. This paper presents a simulation-optimization model for conjunctive use of surface water and groundwater at a basin-wide scale, the Zayandehrood river basin in west central Iran. In the Zayandehrood basin, in the past 10 years, a historical low rainfall in the head of the basin, combined with growing demand for water, has triggered great changes in water management at basin and irrigation system level. The conjunctive use model that coupled numerical simulation with nonlinear optimization is used to minimize shortages of water in meeting irrigation demands for four irrigation systems. Constraints guarantee the maximum/minimum cumulative groundwater drawdown and maximum capacity of irrigation systems. A support vector machines (SVMs) model is developed as a simulator of surface water and groundwater interaction model while a genetic algorithm (GA) is used as the optimization model. Conjunctive use model runs for three scenarios. Results show that the accuracy of SVMs as a simulator for surface water and groundwater interaction model is good and that it is possible to decrease the water shortage for irrigation systems with application of proposed SVMs-GA model.
Keywords Surface water; Groundwater; Conjunctive use; Support vector machines; Optimization; Simulation; Genetic algorithm.
link.springer.com/article/10.1007%2Fs11269-013-0307-2