A Prototype Model-Based Expert System for Agricultural Landscape Analysis
Abstract
Agronomic experts use satellite imagery (land-use maps) to make frequent diagnoses of the Lorraine region's agriculture. Their diagnoses rely on landscape analysis and involves various knowledge and reasoning methods. Their interest is also in mapping various criteria to validate their field experience at a regional scale. They therefore need AI techniques. AI techniques attempt to represent domain knowledge by rules or by ``domain models''. In the current work, the knowledge concerning the relationship between agriculture and landscape has been represented through a ``functional model of agricultural landscape'': the model components are image regions which have properties and relations whose combination expresses the global functioning of the agricultural system. This model has been implemented through a multi-agent blackboard based architecture. The prototype has been applied on images of a small part of the Lorraine region, initially to characterize and classify plots and village areas. The first results are very interesting for experts who can then deepen their analysis and improve the model.
Domains
Artificial Intelligence [cs.AI]
Origin : Files produced by the author(s)
Loading...