This report presents the results of the literature review and the initial investigation into the most appropriate methods for forecasting foot-by-foot track geometry data. Point processing with the SARIMAX model and segment processing with Meta’s Prophet model both produced accurate forecasts for these data. Adding exogenous variables to both models to account for unexpected track maintenance between measurements significantly improved the predictions. Using these models, along with frequent Autonomous Track Geometry Measurement System (ATGMS) measurements, can accurately predict the future behavior of track geometry and help plan preventive maintenance more effectively. Case studies applying these methods will be completed as the next step in this research.