The department of Arequipa, Peru is a region in which freshwater management is crucial. Water-use models are thus valuable tools for policymakers in this region. Crop maps made by classification of satellite images, when processed and combined with other models, can offer large-scale estimates of agricultural water needs in a region. Such estimates would be valuable for the farmers and policymakers of Arequipa. The goal of this study was to develop a monthly agricultural water-use mapping algorithm for the agriculture around Arequipa City. This goal was accomplished in three steps. First, a crop-mapping algorithm was created, based on supervised classification methods, high-resolution satellite images, and ground reference data. Ground reference data were collected monthly from September 2019 to February 2020. Secondly, a crop growth-stage prediction algorithm for the crop maps was created. Finally, an algorithm for creating agricultural-water-demand maps using the results of steps 1 and 2 and auxiliary CROPWAT data was made. The crop-mapping algorithm was shown to create maps with acceptable accuracy, with 5 maps having mean accuracies of 69% or greater, (6th month = 61%). The growth-stage prediction algorithm was found to be an accurate predictor of age, with 88% or more of all predictions being within +/- 1 month of the reference ages for 5/6 months (6th month = 72%). Water demand maps were produced in units of mm/month, allowing for easy integration of areas of interest. This study provides immediately useful results and, more importantly, a framework for future large-scale agricultural-water-use mapping in the region.