Knowledge-based fertilization recommendation system and application

Crop fertilization recommendation system involves using models to calculate the needed amount of variety of nutrients during the crop growth, choosing suitable fertilizers, and arranging fertilization time. Whether it can be used widely or not, the key point is that the models or parameters in system can be customized easily with local agricultural production practices. To help address these issues, a software infrastructure is proposed. It adopts concepts form knowledge base with the aim of providing an overall logical framework for fertilization recommendation, in which the knowledge base as the interface between local entities and program code, and the professional fertilization mechanism as the inference engine. This paper discusses the fertilization knowledge’s classification, representation, storage and the relations with data entities, and presents the design of knowledge base and its application. Based on this method, a practical software system for cultivated land quality and fertilization management has been developed by integrating with GIS, and the scalability and localizability has been demonstrated by more than thirty counties’ cases.