Developing Knowledge Based Recommender System for Crop Selection

The most important role that agriculture plays in a country’s political, economic and social stability makes degree of agricultural productions seriously sensitive. Agricultural production patterns vary markedly over Ethiopia according to agro-climatic conditions, in specific, broadly varying rainfall and elevation. To increase the cultivation process and improve agricultural productivity it is also require knowledge-based recommender system for crop selection, in order to advice how the farmers and experts select the crop type by considering soil texture, soil PH value, temperature, average rainfall, and other factors.

Knowledge-based systems are a branch of artificial intelligence which is a computer program that attempts to replicate the reasoning processes of a human expert. It can make decisions and recommendations and perform tasks based on user input. The expert`s knowledge is accessible when the human expert might not be and so that the knowledge can be accessible at all times and in numerous places, as necessary. Cultivators (farmers) need advance or specialist knowledge to take decision during soil preparation, seed selection, fertilizer management, pesticide management, water planning, weed management etc., so that to get high yield. In Ethiopia Current cereal yields are low, by international standards, indicating growth potential, since of lack of advanced agriculture experts and shortage of agriculture facilities. In the efforts to address such problems, it is important to develop Knowledge-based system recommender system that can provide advice for farmers and agriculture professionals to facilitate crop selection process to become more productive.

In this study, a prototype knowledge-based system (KBS) recommender system for crop selection is proposed. So, in order to develop the proposed recommender system an implicit and explicit knowledge used and acquired through interview, document analysis respectively. The data were collected from Gondar Agricultural Research Center which is found in Ethiopia. Knowledge Engineering research design was employed to develop the system. The prototype system reaches a good performance and meets the goals of the study.