عنوان مقاله [English]
Developing optimal operating policies for conjunctive use of surface and groundwater resources when different decision makers and stakeholders with conflicting objectives are involved is usually a challenging task. This problem would be more complex when objectives related to surface and groundwater quality are taken into account. In this paper, a new methodology is developed for real time conjunctive use of surface and groundwater resources. In the proposed methodology, a well-known multi-objective genetic algorithm, namely Non-dominated Sorting Genetic Algorithm II (NSGA-II) is employed to develop a Pareto front among the objectives. The Young conflict resolution theory is also used for resolving the conflict of interests among decision makers. To develop the real time conjunctive use operating rules, the Probabilistic Support Vector Machines (PSVMs), which are capable of providing probability distribution functions of decision variables, are utilized. The proposed methodology is applied to Tehran Aquifer inTehran metropolitan area,Iran. Stakeholders in the study area have some conflicting interests including supplying water with acceptable quality, reducing pumping costs, improving groundwater quality and controlling the groundwater table fluctuations. In the proposed methodology, MODFLOW and MT3D groundwater quantity and quality simulation models are linked with NSGA-II optimization model to develop Pareto fronts among the objectives. The best solutions on the Pareto fronts are then selected using the Young conflict resolution theory. The selected solution (optimal monthly operating policies) is used to train and verify a PSVM. The results show the significance of applying an integrated conflict resolution approach and the capability of support vector machines for the real time conjunctive use of surface and groundwater resources in the study area. It is also shown that the validation accuracy of the proposed operating rules is higher that 80% and based on these rules, the cumulative groundwater table variation is limited to 80 centimetres during a 15-year planning horizon.
1- Emch, P.G., and Yeh, W.W-G., (1998). “Management model for conjunctive use of coastal surface water and groundwater.” J. of Water Resources Planning and Management, 124 (3), 129-139.
2- Azaeiz, M.N.(2002). “A model for cunjunctive use of ground and surface water with opportunaty costs.” European j. of Operation Research, 143, 611-624.
3- Karamouz, M., Kerachian, R., and Zahraie, B. (2004) “Monthly water resources and irrigation planning: Case study of conjunctive use of surface and groundwater resources.” J. of Irrigation and Drainage Engineering, 130, 93-98.
4- Karamouz, M., Rezapour Tabari, M. M., and Kerachian, R. (2007) “Application of genetic algorithm and artificial neural networks in conjunctive use of surface and groundwater resources.” Water International, 32, 163-176.
5- Rezapour Tabari, M. M., Maknoon, R., and Ebadi, T. (2009). “Multi-objective optimal model for surface and groundwater conjuctive use management using SGAs and NSGA-II.” J. of Water and Wastewater, 69, 2-12. (In Persian)
6- Rezapour Tabair, M. M., Maknoon, R., and Ebadi, T. (2009). “Conjuctive use management under uncertainty in aquifer parameters.” J. of Water and Wastewater, 72, 2-15. (In Persian)
7- Bazargan-Lari, M. R., Kerachian, R., and Mansoori, A. (2009). “A conflict-resolution model for the conjunctive use of surface and groundwater resources that considers water-quality issues: A case study.” Environmental Management, 43, 470-482.
8- Kerachian, R., Fallahnia, M., Bazargan-Lari, M. R., Mansoori, A., and Sedghi, H. (2010). “A fuzzy game theoretic approach for groundwater resources management: Application of rubinstein bargaining theory.” Resources Conservation and Recycling, 54 (10), 673-682.
9- Vapnik, V. (1995). The nature of statistical learning theory, Springer-Verlag, NewYork.
13- Asefa, T., Kemblowski, M., McKee, M., and Khalil, A. (2005). “Multi-time scale stream flow predictions: The support vector machines approach.” J. of Hydrology, 318, 7-16.
14- Safavi, H. R., Afshar, A., Ghaheri, A., Abrishamchi, A., and Tajrishi, M. (2007). “A quality-quantity simulation mode for stream-aquifer interaction.” J. of Water and Wastewater, 61, 2-14. (In Persian)
15- Deb, K., Agrawal, S., Pratap, A., and Meyarivan, T. (2000). A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II, KANGAL Rep. No. 200001, Indian Institute of Technology,Kanpur,India.
16- Cortes, C., and Vapnik, V. (1995). “Support-vector network.” Machine Learning, 20, 273-297.
17- Burges, C. J. C. (1998). “A tutorial on support vector machines for pattern recognition.” J. Data Mining and Knowledge Discovery, 2(2), 1-47.
18- Wu, T. F., Lin, C. J., and Weng, R. C. (2004). “Probability estimates for multi-class classification by pairwise coupling.” J. Machine Learning Research, 5, 975-1005.