Studies of the early universe hinge on high redshift observations. At high redshifts the UV will be shifted into the Optical regime. By studying nearby supernovae in the UV we can gain an understanding of the physics behind high red-shifted distant observations. Ultra Violet/Optical Telescope (UVOT) instruments such as the Neil Gehrels Swift Observatory are excellent platforms for studying nearby UV sources such as Type IIn supernovae. Observations of the early epochs of these supernovae remain scarce, necessitating the development of numerical and semi-numerical models of these supernovae. In this research we will be taking an existing semi-numerical model and expanding its handling of the opacity of the photosphere and Circumstellar Medium and comparing the results to both the existing model’s results and to the existing catalog of IIn supernovae in the Swift archive, confirming the validity of the new model. In addition, we will develop Machine Learning (ML) IIn classifiers using synthetic data produced from the model. These classifiers can later be used to direct Swift targets of opportunity pulled from all sky surveys such as The Vera Rubin Observatory Legacy Survey of Space and Time (LSST) mission as they become available. We will present results of our comparison of opacity changes to the existing model and present preliminary results of our ML classifier.