Katachi: Decoding the Imprints of Past Star Formation on Present Day Morphology in Galaxies with Interpretable CNNs
Authors:
- Juan Pablo AlfonzoJAJuan Pablo Alfonzo
- Kartheik G. IyerKIKartheik G. Iyer
- Masayuki AkiyamaMAMasayuki Akiyama
- Greg L. BryanGBGreg L. Bryan
- Suchetha CooraySCSuchetha Cooray
- Eric LudwigELEric Ludwig
- Lamiya MowlaLMLamiya Mowla
- Kiyoaki C. OmoriKOKiyoaki C. Omori
- Camilla PacificiCPCamilla Pacifici
- Joshua S. SpeagleJSJoshua S. Speagle
- John F. WuJWJohn F. Wu
Preprint
Abstract
The physical processes responsible for shaping how galaxies form and quench over time leave imprints on both the spatial (galaxy morphology) and temporal (star formation history; SFH) tracers that we use to study galaxies. While the morphology-SFR connection is well studied, the correlation with past star formation activity is not as well understood. To quantify this we present Katachi, an interpretable convolutional neural network (CNN) framework that learns the connection between the factors regulating star formation in galaxies on different spatial and temporal scales. Katachi is trained on 9904 galaxies at 0.02$<$z$<$0.1 in the SDSS-IV MaNGA DR17 sample to predict stellar mass (M$_*$; RMSE 0.22 dex), current star formation rate (SFR; RMSE 0.31 dex) and half-mass time (t$_{50}$; RMSE 0.23 dex). This information allows us to reconstruct non-parametric SFHs for each galaxy from \textit{gri} imaging alone. To quantify the morphological features informing the SFH predictions we use SHAP (SHapley Additive exPlanations). We recover the expected trends of M$_*$ governed by the growth of galaxy bulges, and SFR correlating with spiral arms and other star-forming regions. We also find the SHAP maps of D4000 are more complex than those of M$_*$ and SFR, and that morphology is correlated with t$_{50}$ even at fixed mass and SFR. Katachi serves as a scalable public framework to predict galaxy properties from large imaging surveys including Rubin, Roman, and Euclid, with large datasets of high SNR imaging across limited photometric bands.Keywords
All Related Versions
This publication has 91 references indexed in Scilit:
- The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveysPublications of the Astronomical Society of Australia, 2023
- Aging of galaxies along the morphological sequence, marked by bulge growth and disk quenchingAstronomy & Astrophysics, 2022
- Interpreting automatic AGN classifiers with saliency mapsAstronomy & Astrophysics, 2021
- Array programming with NumPyNature, 2020
- SciPy 1.0: fundamental algorithms for scientific computing in PythonNature Methods, 2020
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019
- Galaxy morphology classification with deep convolutional neural networksAstrophysics and Space Science, 2019
- Bulges and discs in the local Universe. Linking the galaxy structure to star formation activityAstronomy & Astrophysics, 2017
- Astropy: A community Python package for astronomyAstronomy & Astrophysics, 2013
- Morphological Transformation from Galaxy HarassmentThe Astrophysical Journal, 1998