Knowledge of future land use changes is crucial, as they are interlinked to various factors of human-environmental systems. Land use changes have a profound impact on urban planning, environmental sustainability, resource management, and overall quality of life. Spatial data can often be computationally heavy, so the provision of accessible and ready-to-use tools is crucial for the analysis of land use changes in any case study. In this work, a Cellular Automata Markov (CAM) model is presented and applied through a combination of Geographic Information Systems (GIS) and Python, to predict land changes and provide future land use maps. The inputs are historical land use maps at a five-year time-step from 2006 to 2021, and the outputs include future land use maps until 2051. The Cedar Creek Watershed (CCW) in Indiana, US, is used as a case study; it is an area of great natural beauty, mainly consisting of agricultural lands, forests and water bodies. Various validation techniques are explored for the predicted maps, based on the historical data, including Accuracy, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), the Kappa coefficient (κ), and Confusion Matrix statistics. The results indicated a gradual increase in urban areas at the expense of agricultural land. Forested areas showed stability with minimal change, while water bodies maintained consistent coverage. Some minor shifts from barren land to both urban and forested categories were also observed. Validation results showed a high accuracy of 99.63%, a mean absolute error (MAE) of 0.0094, and a root mean square error (RMSE) of 0.1613. The Kappa coefficient indicated strong agreement at 0.9925. A step-by-step GIS guide and the Python script are provided to contribute to the reproducibility and improvement of the model. Similar analyses can find multiple applications in a variety of studies on human-environmental systems (including water, agriculture, economy).