Time collection clustering algorithms (TSCAs) are of increasing significance within the evaluation and interpretation of hyper spectral image (HSI) facts. TSCAs are being used to become aware of spatiotemporal styles of spectral characteristics in HSI records by identifying areas of interest (ROIs) which can be associated with physical techniques and mapping the ones ROIs to clusters. One-of-a-kind clustering algorithms may be used to analyze HSI statistics and tease out diffused spatiotemporal modifications. This paper investigates the software of two exceptional TSCAs, particularly okay-method clustering and Self-Organizing Maps (SOMs) to HSI datasets.The SOM set of rules changed into additionally capable of phase the hyperspectral facts into meaningful clusters primarily based on their spectral traits. The accuracy of the SOM results was also assessed.