QUANTITATIVE MANAGEMENT OF GROUNDWATER USING BAYESIAN DECISION NETWORK

In recent years, quantity and quality of groundwater in most country is reduced due to over-withdrawal of water. It is important to use new tools and technology to manage these water resources. The purpose of this study was to manage the groundwater resource using a Bayesian Decision Network (BDN). The Kordkooy region in North of Iran (Golestan province) has been selected as the study area. The region has been divided to three parts based on transmisivity (T) and electrical conductivity (EC) values. The BDN parameters-marginal probabilities and Conditional Probability Tables (CPTs)-have been identified for each of the three zones. Three groups of management scenarios have been developed based on the two decision variables including "Crop pattern" and "Domestic water demand" across the three zones of the study area. Arising from implementing each scenario have been predicted using the functional BDN for each of the zones. The results showed that unmanaged operation causing irreparable damage to the groundwater of study area. In conclusion, we can propose that the use of BDNs in groundwater management studies is a practical and effective approach for assessing and managing these valuable water resources in a probabilistic context representing the uncertainties.