Recent advances in computer technology have made possible the
development of expert systems. Expert systems are computer programs that
perform at the level of a human expert. Expert systems can help integrate and
apply diverse sources of information and expertise to problems of integrated
crop management. A prototype Crop Management eXpert (CMX) system has
been developed. The primary goal of CMX is to provide recommendations on
optimal irrigation and fertilization scheduling for wheat production in the Pacific
Northwest. This system can be used by farmers and/or extension agents.
OUS II Shell has been used as a implementation tool. To build this rule - based
expert system, a development strategy, commonly used in the construction of
expert systems, consisting of 1 ) identification; 2) conceptualization; 3)
formalization; 4) implementation; and 5) testing was applied.
CMX is composed of modules for irrigation and fertilization management.
For irrigation management, CMX is mainly involved in the irrigation scheduling
which is the major part of irrigation management. Irrigation strategies have been
applied in irrigation decision making. For each strategy, timing criteria which
generally consist of management allowed depletion, soil water potential, leaf
water potential, and water stress indices have been used. The system provides
farmers with irrigation scenarios which determine when and how much water to
apply.
CMX represents an integration of conventional computing and expert
systems technology designed to provide expert recommendations enabling
farmers to obtain the best return on their water and fertilizer investment. For
fertilization management, a variety of variables have been taken into considered.
Crop growth stages, soil moisture, nutrient analysis, protein requirement, and
application methods are important factors for the fertilizer decision making.
Several constraints have been used in optimal fertilizer advice.
CMX can focus only on relevant information, thus reducing the problem
space to a manageable size and significantly, improving the efficiency of the
system. The facility of the expert system to explain the decision-making process
enables users to better understand the underlying assumptions, facts, and
reasoning used to generate recommendations. The CMX prototype
demonstrates the feasibility of employing expert systems technology in
agricultural applications.
CMX has been validated and evaluated. The survey results showed that
this prototype was successful in capturing domain experts' knowledge as rules
and providing advice on the irrigation and fertilization management for wheat. / Graduation date: 1993
Identifer | oai:union.ndltd.org:ORGSU/oai:ir.library.oregonstate.edu:1957/36457 |
Date | 23 October 1992 |
Creators | Cao, Weidong |
Contributors | Bolte, John P. |
Source Sets | Oregon State University |
Language | en_US |
Detected Language | English |
Type | Thesis/Dissertation |
Page generated in 0.0099 seconds