52-Artificial Neural Networks and Multi Criterion Decision Making in Performance Evaluation of an Irrigation System

Abstract

The selection of the best irrigation subsystem is examined in the multiobjective context. Mabi Bajaj Sagar Project, a major irrigation project in India is taken for the case study. Three phase methodology is proposed to rank the irrigation subsystems. In the first phase, payoff matrix for sixteen irrigation subsystems is formulated considering seven performance indicators namely, land development works (LDW), supply of inputs (SI), conjunctive use of water resources (CUW), participation of farmers (PF), economic impact (El), crop productivity (CP) and quality of water for irrigation (QW). In the second phase, Kohonen neural networks (KNN) based classification algorithm is employed to sort the irrigation subsystems into smaller groups. In third and final phase, a Multicriterion Decision Making (MCDM) method, namely, Analytic Hierarchy Process (AHP) is employed to rank the groups obtained from the second phase. It is concluded that the proposed methodology is useful and can be extended to situations where number of irrigation subsystems and criteria are larger in number.