Modeling and simulation of a multi-parametric fuzzy expert system for variable rate nitrogen application

Nitrogen (N) excess due to mineral fertilization in conventional crop farming has a significant negative impact on the environment. Variable rate N application (VRNA) is a promising tool to increase N recovery rates in spatially heterogeneous fields. Real-time sensor systems for VRNA usually consider only the crop?s N status and their fertilization algorithms are abundantly deterministic. Due to their education and professional experience, farmers have a considerable knowledge base that should be used to describe the dynamic and non-deterministic interactions of multiple parameters for a locally adapted N fertilization. Fuzzy systems present an effective way to integrate expert knowledge into an automated multi-parametric control. This paper describes, how fuzzy logic can be used to fuse the plant-related information from a real-time sensor system with further parameters to create a multi-parametric system for VRNA. Using sets of input?output data acquired with a Yara N-Sensor ALS2 system, an adaptive, fuzzy logic-based model of its agronomic algorithms was identified, optimized and validated. The results indicated high accordance with the N-Sensor algorithms and good automated adaptability to different calibrations with values of the Pearson correlation coefficient higher than 0.99 and a maximum percentage root mean square error of 0.14%. In a case study, the model was combined with the apparent soil electrical conductivity (ECa) as an indicator for spatially varying soil productivity, as well as a case distinction for different weather conditions. Simulations with historic ECa data and N-Sensor recordings have shown the high flexibility of the multi-parametric fuzzy expert system. With the presented method, specific deficiencies of one-parametric approaches can be moderated and the application can be adapted to the prevailing conditions in a straightforward manner. Also, the target orientation could be influenced based on the specific preferences of the expert.