The objective of this study is to generate and compare prospectivity maps that show the presence of Limestone in a specific area using remotely sensed data and machine learning techniques, in order to determine the most precise map that accurately depicts the presence of Limestone in that area. Remotely sensed data often utilize machine learning techniques to identify mineral formations and map geological features. Furthermore, machine learning techniques can also be used to generate prospectivity maps for mineral exploration. In this study, we utilized band ratios and principle component analysis (PCA) in conjunction with machine learning techniques to effectively identify Limestone formations and generate prospectivity maps for Limestone exploration using satellite imagery. Support Vector Machines (SVM) and Neural Networks (NN) were the machine learning techniques utilized on multispectral imagery from Sentinel-2 and Landsat-8. To assess the accuracy of the identification, the confusion matrix and kappa coefficient were employed. It was determined that the accuracy of the Neural Networks (NN) techniques was significantly better than the accuracy of the Support Vector Machines (SVM) techniques. The Neural Networks (NN) achieved an accuracy of 94.92% with a kappa value of 0.929, whereas the Support Vector Machine (SVM) had a maximum accuracy of 88.39% with a kappa value of 0.845. These high levels of accuracy and kappa coefficient values suggest that these machine techniques hold great potential for geological mapping and mineral exploration. The generated prospectivity maps can assist geologists and mining companies in identifying areas with a high potential for Limestone exploration, thereby reducing exploration costs and time.