Being able to identify strongly-lensed galaxies in wide-field, low-resolution imaging opens up a number of research possibilities from cosmology to galactic evolution to the study of the distribution of baryonic and dark matter in the lenses. To accomplish this, we have used training data composed of known lens systems from the Master Lens Database and the DESI Bright Arcs Survey. Our imaging data comes from the DECaLS and WISE surveys (using the g,r,z, W1, and W2 filters) and uses the photometry measurements and uncertainties generated from the probabilistic astronomical source detection and measurement software package Tractor. This data is then fed into the stellar population modeling code Prospector (Johnson et al., 2019) which allows us to generate synthetic best fits to the galaxy photometry. We have applied two machine learning techniques (a gradient boosted classifier and a CNN) that allow us to identify potential lens systems with high accuracy. Here we describe the workflow to generate the necessary input data and our findings.