In recent decades, limited surface water resources and increasing water demand causes additional pressure on aquifers and irreparable damage to natural resources. Conjunctive use of surface water and groundwater is an effective approach to relief water resources shortages and its uneven temporal and spatial distribution in arid inland. In the Zayandeh-Rud River Basin, in the past 10 years, a historical low precipitation 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. In this research, the conjunctive use policies for surface water and groundwater resources of Najafabad sub basin located in Zayandeh-Rud river basin under uncertainty of demand and water supply is achieved through Bayesian Networks (). A Bayesian Network consists of a graphical structure and a probabilistic description of the relationships among variables in a system. are techniques to assist decision-making and are especially helpful when there is uncertainty in the data and the factors are highly interlinked. The trained are able to estimate water table levels in the aquifer agricultural areas, under monthly water management policy. Three management scenarios under climate change scenario A 2 were defined and its impacts on the plain were investigated over the next 5 years. The first scenario’s aim is to continue the current trend of extraction of groundwater, in the second scenario decrease pumping from the wells, and in the third scenario increase the surface water to irrigation channels. Results of different scenarios have shown that the reduction in pumping is the main causes of the drawdown in groundwater level. Based on the result of this study, the developed policies are able to control groundwater depletion in the study area. They also show importance of integrated approach for allocation surface water and groundwater resources in the Najafabad plain. Keywords: Conjunctive Use, Bayesian Networks, Uncertainty, Najafabad Plain, Water Resources Management, Groundwater Level
