NEPER WHEAT: AN INTEGRATED ARCHITECTURE FOR IRRIGATED WHEAT CROP MANAGEMENT

摘要

In this report, we discuss the development of an integrated system for irrigated wheat crop management in Egypt. The goal of our work is to develop a system that will address the various aspects of crop management including varietal selection, planting/harvest date selection, sowing parameters decisions, insect/disease/weed identification and remediation, irrigation/fertilization management and harvest management. The approach we take to solve this problem is the Generic Task Approach to expert systems development pioneered by Chandrasekaran et al. By using the Generic Task (GT) approach, we set out to model the behavior of an expert in wheat crop management. Previous research in the Generic Task approach has typically focused on the application of a single generic task problem solver to solve a particular problem. However, as a multi-task problem, wheat crop management calls for the cooperation of multiple problem solvers, each tackling a portion of the larger problem. Thus, wheat crop management provides a testbed for the idea of integrating multiple generic tasks together with the numeric simulation capabilities of CERES Wheat pioneered by Ritchie et al. We use the Knowledge Level Architecture proposed by Sticklen as the template by which we will organize our system.