Mixed-phase conditions impact cloud radiative effects, precipitation processes, and cloud lifetimes. Despite their importance, mixed-phase cloud effects are difficult to correctly simulate due to a lack of understanding of the microphysical processes involved, particularly in convective clouds. To improve our understanding of mixed-processes we need additional observations to characterize when mixed-phase conditions exist and how they relate to cloud dynamics and atmospheric environment. This study applies machine learning to identify cloud phase in Doppler spectra moments from vertically pointing Ka-band Doppler radars at the US Department of Energy Atmospheric Radiation Measurement (ARM) sites. The ability to detect mixed-phase conditions in the stratiform regions of deep convection and in convective clouds with weak updrafts is investigated using k-means clustering of spectra moments. Doppler spectra data is harder to interpret in deep convective clouds due to high turbulence and precipitation which broaden and attenuate the signal respectively. Despite these challenges, a mixed-phase signature can be seen in the clouds, and the potential for an automated algorithm is shown using data from the ARM Southern Great Plains site. The phase identification from the Ka-Band measurements is compared to signatures from other instrumentation such as hydrometeor identification in lower frequency precipitation radars and the Raman Lidar, and progress on an automated algorithm will be shown. An automated algorithm has the potential to produce statistics of the frequency of mixed-phase conditions within clouds, which is needed to better understand the prevalence of microphysical growth mechanisms like the Wegener Bergeron Findeisen process.