Je
is
al
of
ip
id
DESIGN OF AGRICULTURAL DISASTER EVALUATION SYSTEM BASED ON GIS, SIMULATION AND
EXPERT-SYSTEM TECHNIQUES
Zhu Zesheng, Sun Ling
Nanjing Navy Institute of Electronic Engineering, Nanjing, JiangSu, 210017, P. R. China
JiangSu Academy Of Agricultural Sciences, Nanjing, JiangSu, 210014, P. R. China
Commission VII, Working Group 7
KEY WORDS: Agriculture, Management, GIS, Project
ABSTRACT
The agricultural industry is more complex, dynamic, and competitive. Agricultural disaster evaluation system( ADES)
has become an important tool and technology in modern agricultural production. However, how to design such system
has been being a very important and complex problem with the help of advanced information processing, techniques
such as GIS, simulation and expert system. In this paper, we present a new method for the design and implementation
of ADES. this method is based on a new layered architecture model which is used to design and implement complex
ADES. The model integrated reasonably GIS, simulation models and expert system in ADES and simplified its design
and implementation. Otherwise, an excellent commercial GIS environment was used as a tool for the integration.
ADES provides a number of important information and decisions for senior managers of agricultural production as
well as plays a very important role in the production. Finally, we discuss a typical application of ADES in dangerous
weather disaster warning of stored grain management.
1. INTRODUCTION
Today, the agricultural industry is more complex,
dynamic and competitive. Many factors such as biology,
weather, disaster, economics and market influence
interactively this business(Liang, 1986). In recent years,
Agricultural Disaster Evaluation System(ADES) has
been being widely researched and fast developed, in
which it not only is playing a more important role, but
also has become a very important tool of production
management in modern agricultural production.
However, how to reasonably apply various existent
information processing techniques for designing and
implementing excellent performance ADES has been a
very important and interesting problem in field of
agricultural production management. Unfortunately,
ADES design and implementation is also a very complex
and difficult problem for most of agricultural
applications. Major reason resulting in the situation is
that ADES must process a lot of information relevant to
agricultural disasters(especially including some random
or undetermined information) and provide precise
decision information for ADES users. Otherwise,
another reason includes that the work to build ADES
model for implementing satisfactory ADES is also very
difficult. Thus, the number of existent ADES” not only is
much limited, but those ADES function, quality and
performance are usually unsatisfactory in many
applications of agricultural disaster evaluation. However,
our research on ADES shown that a new effective
673
method for designing and implementing ADES that
satisfies the performance required by user can be used to
solve the above problems and overcome the relevant
difficulties. Further, the new method provides really an
approach to building excellent performance ADES
model. Then, the model supports fast and reasonable
implementation of ADES.
In this paper, we present this new method of building
ADES model or ADES. This method includes three key
information processing techniques such as geographic
information system(GIS), simulation and expert
system(ES) techniques. Really, they are also the most
important techniques for implementing excellent
performance ADES. The ADES based on this method
not only makes use of advantages of those techniques as
more as possible, but also has much better performance
and more users than existent ADES.
2. ADES ARCHITECTURE MODEL
One of the most important tasks to design ADES is
carefully to determine its various function parts and to
build the logical relationship between those parts, so that
those parts and relationship are used to construct ADES
architecture model. However, in practical applications,
ADES involves decision-making based on complex
interactions between people, pests, lands, crops, natural
disasters, and other natural resources relevant to
agricultural disasters. Modeling these interactions and
representing them in ADES for supporting decision
International Archives of Photogrammetry and Remote Sensing. Vol. XXXI, Part B7. Vienna 1996