The goal of data mining is to obtain relevant data from a large data set. Because of the advances in camera IT, and high-performance computing, a vast amount of knowledge is accessible in a broad variety of science disciplines. Not only are these data sets incredibly wide but they are often quite complicated to be represented in terabytes and petabytes. The whole complexity occurs as the data is generated by various sensors at varying intervals, wavelengths, or resolutions. In reality, the awareness is typically interpreted or meshed and has both a spatial and a temporal aspect often. This array of data is generated in different fields, including astronomy, medical imaging, remote sensing, non-destructive analysis, physics, the science of materials & bioinformatics. This increasing size and complexity of scientific disciplines have led to a challenging problem. Many of the conventional methods of analysis and analytics used to interpret these data were becoming obsolete. Visualization approaches are inefficient due to their subjective nature and human weakness, except in the case of moderate sample scales, where is statistical techniques cannot exceed large data sets. As a consequence, much of the gathered data was never really processed and the complete value of our advanced data collection capability is only partially recognized. The data mining method includes the recovery of data trends, correlations, trends, and statistically relevant data structures. This is a process involving preprocessing of data, display of model search & findings, and iterative and interactive validation. It is a multidisciplinary area that aims to take concepts