Introducing Fuzzy Cognitive Maps for decision making in precision agriculture

Abstract

A Fuzzy Cognitive Maps (FCMs) is a modelling 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 (describing elements of the system) 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. 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 cotton yield and of the weighted relationships between these nodes. The nodes of the FCM model represent the main factors influencing cotton crop production i.e. essential soil properties such as texture, pH, OM, K, and P. The proposed FCM model addresses the problem of crop development and spatial variability of cotton yield, taking into consideration the spatial distribution of all the important factors affecting yield. The first results of the study are very promising; our model achieves a 70% average success rate on yield class prediction between two possible categories (low and high) for three different years. This model will be further investigated to achieve better results by introducing learning algorithms into FCMs.