During the last twenty-five years the scarcity of water resources is exponentially growing worldwide. As a result, there has been a serious and growing concern about the water shortage problem, resulting in substantial progress in different aspects of water resource development and management in different parts of the world. The problem of the scarcity of water is especially severe in the semi-arid countries and in particular, in the coastal and island communities of the Mediterranean region, where the satisfaction of water demand is not possible. Cyprus situated in the north east part of the Mediterranean region is among the countries facing a severe water shortage problem and focusing in finding efficient and systematic ways for effective water management.

This paper describes an interdisciplinary, intelligent and flexible decision support system addressing the highly complex problem of the management of water resources in the regions along the South Conveyor Project (SCP), the largest water development project in Cyprus. The proposed decision support system is based on a heterogeneous, hybrid architecture integrating together a variety of technologies and targets the development of an integrated, holistic approach to manage water and replace use-based management. Such a scientific approach allows information management, knowledge elicitation, prediction of the future, exploration of alternatives but mainly systematic decision making on the operational activities involved, providing methods for handling the interdisciplinary nature of water management and the measurement of the effectiveness of the decisions taken.

The proposed decision support system embodies deep knowledge in the form of causal loop modeling and uses systems dynamics and simulation modeling for case-base reasoning that performs inferencing at a high level. It also involves relational databases for data storage, analysis and representation, and employs data pre-processing and standard statistical techniques for intelligent data analysis and forecasting. Its components can evolve on the basis of input data and expert knowledge. All these disciplines equip the system with intelligence and allow it to reason under uncertainty, increasing in that way efficiency and accuracy in the management of water. The system’s interactions is achieved through complicated and well-designed GUIs, which utilize a number of communication and integrating techniques.

This system is developed in the context of the INCO-DC project MEDWATER whose overall target is the management of water resources in the Mediterranean region. The duration of this project was three years (Nov 1997 – Oct 2000) and its overall financial support from the EU was 0.5M Euro. The system to be presented is mainly the result of a close collaboration between the University of Cyprus and the Water Development Department (WDD) in Cyprus. Given the nature of the problem, an interdisciplinary consulting team, consisting of water engineers, hydrologists, computer scientists and statisticians was necessary for addressing all aspects of the problem.

The resulting decision support system will be installed at the WDD. Experimental results on real data will be presented, analyzed and used for further reasoning and decision making. The benefits accruing from the use of the system are expected to be highly significant.

Keywords: Water Management, Decision Support Systems, Hybrid Architectures, Causal Loops, Systems Dynamics, Simulation and Regression Models.