 The study proposes an optimal workflow for producing baseline LULC input images from Landsat sensor data, and identifies the most efficient way to configure land change drivers and regional comprehensive plan prescriptions in creating future LULC data sets for a regional watershed. The results show that an object-based hybrid classification approach improves projected images with a 15% increase in AUC value compared to a pixel-based method, while configuring anthropogenic drivers in a trend format rather than individual year values can improve the training of a multi-layer perceptron neural network, Markov chain model. The calibrated and validated model predicts that residential, commercial, institutional, green vegetation shrub, and industrial LULC will grow through 2050 at a slower rate, 12% compared to the contemporary period, 39%, while forest and agricultural lands are expected to decline, minus 2%. This article was offered by Cyril O. Wilson, Bing Qingliang, and Shannon J. Rose. We are article.tv, links in the description below.