An application of PCA and fuzzy C-means to delineate management zones and variability analysis of soil

Within-field variability is a well-known phenomenon and its study is at the centre of precision agriculture (PA). In this paper, site-specific spatial variability (SSSV) of apparent Electrical Conductivity (EC_a) and crop yield apart from pH, moisture, temperature and di-electric constant information was analyzed to construct spatial distribution maps. Principal component analysis (PCA) and fuzzy c-means (FCM) clustering algorithm were then performed to delineate management zones (MZs). Various performance indices such as Normalized Classification Entropy (NCE) and Fuzzy Performance Index (FPI) were calculated to determine the clustering performance. The geo-referenced sensor data was analyzed for within-field classification. Results revealed that the variables could be aggregated into MZs that characterize spatial variability in soil chemical properties and crop productivity. The resulting classified MZs showed favorable agreement between EC_a and crop yield variability pattern. This enables reduction in number of soil analysis needed to create application maps for certain cultivation operations.