Soft Computing Technique of Fuzzy Cognitive Maps to connect yield defining parameters with yield in Cotton Crop Production in Central Greece as a basis for a decision support system for precision agriculture application

This work investigates the yield and yield variability prediction in cotton crop. Cotton crop management is a complex process with interacting parameters like soil, crop and weather factors. The soft computing technique of fuzzy cognitive maps (FCMs) was used for modeling and representing experts’ knowledge. FCM, as a fusion of fuzzy logic and cognitive map theories, is capable of dealing with uncertain descriptions like human reasoning. It is a challenging approach for decision making especially in complex environments. The yield management in cotton production is a complex process with sufficient interacting parameters and FCMs are suitable for this kind of problem. The developed FCM model consists of nodes that represent the main factors affecting cotton production linked by directed edges that show the cause-effect relationships between factors and cotton yield. Furthermore, weather factors and conditions were taken into consideration in this approach by categorizing springs as dry–wet and warm-cool. The methodology was evaluated for approximately 360 cases measured over 2001, 2003 and 2006 in a 5 ha cotton field. The results were compared with some benchmarking machine learning algorithms, which were tested for the same data set, with encouraging results. The main advantage of FCM is the simple structure and the easy handling of complex data.