The purpose of this project is to develop, test, and document performance of dual-domain clustering algorithms for spatiotemporal datasets, tailored to pandemic preparedness and endgame challenges. Dual-domain clustering refers to the unsupervised learning clustering method performed on data with both application-specific attributes (e.g., number of infectious) and geographic information (e.g., latitude and longitude of data instances). The goal of the method is to cluster spatial regions (such as counties) such that there are both distinctions in values of attributes between cluster groups and also geographic cohesion within cluster groups. Dual domain clustering has been performed on static disease incidence data, but we wish to extend to the spatiotemporal case of infectious disease data. In view of this, we desire a ground truth mechanistic model with which to generate spatiotemporal infectious disease datasets to test our unsupervised learning clustering algorithms. Hence, we present a new multi-region SEIR model in which separate SEIR systems for each region are coupled together using mobility terms. We calibrate our model using North Carolina Covid-19 data. Then, we show preliminary results of dual-domain clustering on temporal snapshots of generated data.