Development of a Forecasting Model for Farm Produce using Fuzzy Cognitive Map

Abstract

A Fuzzy Cognitive Maps (FCMs) is a modeling methodology based on exploiting knowledge and experience. It comprises the main advantages of fuzzy logic and neural networks, representing a graphical model that consists of nodes-concepts which are connected with weighted edges (representing the cause and effect relationships among the concepts). FCMs have proved to be a promising modeling methodology with many successful applications in different areas especially for simulating system design, modeling and control. Improving the crop yield has always been a major challenge for farming community as well for agricultural scientists. Though various computational approaches (qualitative and quantitative analysis) have been followed traditionally in practice, still a persistent decision making method to improve crop yield is not yet predicted.
In this work, FCMs are introduced to model a decision support system for precision agriculture (PA). The FCM model developed
consists of nodes which describe soil properties and agricultural crop yield and of the weighted relationships between these nodes. The nodes of the FCM model represent the main factors influencing crop production i.e. essential soil properties such as soil texture, temperature, soil fertility, bulk density, pH, annual rainfall, pest infestation among others.
This work provides a clear understanding to agricultural products yield forecasting. The information obtained at the end of this work will be useful to agricultural scientists, farmers and other stakeholders