Effects of Training Parameter Concept and Sample Size in Possibilistic c-Means Classifier for Pigeon Pea Specific Crop Mapping

This research work aims to study the effect of training parameter concept and sample size in process classification by using a fuzzy Possibilistic c-Means (PCM) approach for Pigeon Pea specific crop mapping. For class extraction, “mean” data is considered as algorithm. In this study, we proposed an “Individual Sample Mean” (ISM) where individual accounted mean PCM classifier. order avoid spectral overlap target pea with other crops area, temporal indices database was generated from Sentinel 2A/2B satellite images acquired during 2019–2020 cycle. The dimensionality reduced extract required bands achieve maximum enhancement data. Further, increased heterogeneity within classified output. ISM delivered higher membership difference (MMD) between co-cultivated Cotton compared conventional method. indicated that better separation achieved spectrally similar grown, were cultivated same area. When gradually 5 60, MMD values test fields remained range 0.013–0.02, thereby implying algorithm works even small number samples. handled since variance obtained field only 0.008, 0.02 approach.