It is possible to define the quantity of temporal effects by employing multitemporal data sets to discover changes in nature or in the status of any object based on observations taken at various points in time. It's not uncommon to come across a variety of different methods for spotting changes in data. These methods can be categorized under a single umbrella term. There are two primary areas of study: supervised and unsupervised change detection. In this study, the goal is to identify the changes in land cover. Covers a specific area in Kayseri using unsupervised change detection algorithms and Landsat satellite pictures from various years have been gleaned through the use of remote sensing. In the meantime, image differencing is taking place. The method will be applied to the photographs using the image-enhancing process. In the next step, Principal Component Analysis (PCA) is employed. The difference image will be analyzed using Component Analysis. To find out which locations have and which do not. As a first step, a procedure must be in place. We've finished registering images one after the other. Consequently, the photos are being linked together. After then, it's back to black and white. Three non-overlapping portions of the difference image have been created. This can be done using the principal component analysis method. From the eigenvector space, we may get to the fundamental components. As a last point, the major feature vector space fuzzy C-Means Clustering is used to divide the component into two clusters, and then a change detection technique is carried out. As the world's population grew, farmland expansion and unplanned land encroachment intensified, resulting in uncontrolled deforestation around the globe. This project uses unsupervised learning algorithm K-means clustering. In a cost-effective manner that can be employed by officials, companies as well as private groups, to assist in fighting illicit deforestation and analysis of satellite database.