An analysis and understanding of forest dynamism over time gives one insightful information on when and how to react to these changing forest trends. For many years now, stakeholders in forestry have used remote sensing for various applications such as the management and assessment of the health of forests, as well as the analysis of forest changes over time. This research delved into the development of an application, chiefly based on Python and its default and external libraries, for forest classification, change detection and time-series analysis, in order to be able to remotely assess the vitality and/or defoliation of forests over time. The developed tool follows a modularized approach such that it contains individual tools for Co-registration, Radiometric Normalization, Classification, and Time-Series Analysis. The tool was developed making use of Python Open Source libraries namely Tkinter, GDAL/OGR, NumPy, SciPy and Scikit-Learn. Tkinter was used in creating the graphical user interface (GUI) of the entire application, GDAL/OGR was used for reading and writing of raster and vector data, NumPy and SciPy were used in the numerical and scientific analysis of the arrays generated from the images, whiles Scikit-Learn, with its Classification and Regression Tree routine, was used for image classification.