Dust and stellar property estimates via machine learning techniques

Large surveys have been performed from the ultraviolet (UV) to the far-infrared (FIR). Some galaxies are observed over this whole wavelength range, and through SED fitting we get accurate estimates of their stellar and dust properties. Unfortunately, most galaxies are only detected at a limited part of this spectrum. With machine learning techniques, we can use the UV-FIR galaxies as a blueprint: we learn the mapping from their fluxes to their properties. For example, a mapping from UV-NIR to dust mass can be established, and then applied to galaxies that lack FIR data. We present this approach using DustPedia and H-ATLAS data, and show the superiority over energy balance SED fitting. Besides what can be directly estimated from the SEDs alone, this technique implicitly uses relations that follow from galaxy evolution. To avoid a black box, we take special care to estimate uncertainties on our predictions and to interpret the model.