Using deep machine learning we show that the internal velocities of galaxies can be retrieved from optical images trained using 4596 systems observed with the SDSS-MaNGA survey. Using only i-band images we show that the velocity dispersions and the rotational velocities of galaxies can be measured to an accuracy of 29 km s−1 and 69 km s−1 respectively, close to the resolution limit of the spectroscopic data. This shows that galaxy structures in the optical holds important information concerning the internal properties of galaxies, and that the internal kinematics of galaxies are quantitatively reflected in their stellar light distributions.

Explaining artificial intelligence or machine learning models is an increasingly important problem. For humans to stay in the loop and control such systems, we must be able to understand how they interact with the world. This work proposes using known or assumed causal structure in the input variables to produce simple and practical explanations of supervised learning models. Our explanations-which we name Causal Dependence Plots or CDP-visualize how the model output depends on changes in a given predictor along with any consequent causal changes in other predictors. Since this causal dependence captures how humans often think about input-output dependence, CDPs can be powerful tools in the explainable AI or interpretable ML toolkit and contribute to applications including scientific machine learning and algorithmic fairness. CDP can also be used for model-agnostic or black-box explanations.Preliminary work under review.

Using deep machine learning we show that the internal velocities of galaxies can be retrieved from optical images trained using 4596 systems observed with the SDSS-MaNGA survey. Using only i-band images we show that the velocity dispersions and the rotational velocities of galaxies can be measured to an accuracy of 29 km s −1 and 69 km s −1 respectively, close to the resolution limit of the spectroscopic data. This shows that galaxy structures in the optical holds important information concerning the internal properties of galaxies, and that the internal kinematics of galaxies are quantitatively reflected in their stellar light distributions beyond a simple rotational vs. dispersion distinction.