Currently, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) transmission is increasingamongst the worlds population at an alarming rate. Reducing the spread of SARS-CoV-2 is paramount forpublic health officials as they seek to effectively manage resources and potential population controlmeasures such as social distancing and quarantine. By analyzing the United States county networkstructure, one can model and interdict potential higher infection areas. County officials can provide targetedinformation, preparedness training, and increased testing in these areas. While these approaches may provideadequate countermeasures for localized areas, they are inadequate for the holistic United States. We solvethis problem by collecting data on coronavirus-19 (COVID-19) infections and deaths from the Centerfor Disease Control and Prevention and a network adjacency structure from the United StatesCensus Bureau. Generalized network autoregressive (GNAR) time series models have been proposed as anefficient learning algorithm for networked datasets. This thesis fuses network science and operationsresearch techniques to univariately model COVID-19 cases, deaths, and current survivors across the UnitedStates county network structure.