Example showing the aging of a human face learned from age labels, and the lowering of the sSFR of a galaxy using sSFR labels.

Abstract:
Context: Generative models open up the possibility to interrogate scientific data in a more data-driven way.
Aims: We propose a method for using generative models for exploring hypotheses in astrophysics and other areas. We use a neural network to show how we can independently manipulate physical attributes by encoding objects in latent space.
Methods: By learning a latent space representation of the data, we can use this network to forward model and explore hypotheses in a data-driven way. We train a neural network to generate artificial data to test hypotheses for the underlying physical processes.
Results: We demonstrate this process using a well-studied process in astrophysics, the quenching of star formation in galaxies as they move from low- to high-density environments. This approach can help explore astrophysical and other phenomena in a way different from current methods based on simulations and observations.

Potential future applications

Potential future applications can include but are not limited to the fields of galaxy formation, galaxy evolution, galactic astronomy, etc., as the Fader Network can be trained on any set of objects associated with a given measured physical property. This makes it a useful tool if one wants to capture and visualize correlations, test hypotheses or explore the space of possible parameters in any kind of scientific setting.

Team Members


Kevin Schawinski

Dennis Turp

Ce Zhang