# Bringing manifold learning and dimensionality reduction to SED fitters

## TL;DR

This paper demonstrates that unsupervised machine learning, specifically self-organizing maps, can visualize and accelerate galaxy property estimation from photometric data, matching traditional methods but with vastly improved speed.

## Contribution

It introduces the use of self-organizing maps for galaxy SED analysis, enabling faster estimation of physical properties and better understanding of data-to-parameter mappings.

## Key findings

- SOMs effectively visualize SED model libraries in photometry space.
- SOMs provide accurate physical parameter estimates for galaxies.
- The method is up to a million times faster than traditional SED fitting.

## Abstract

We show unsupervised machine learning techniques are a valuable tool for both visualizing and computationally accelerating the estimation of galaxy physical properties from photometric data. As a proof of concept, we use self organizing maps (SOMs) to visualize a spectral energy distribution (SED) model library in the observed photometry space. The resulting visual maps allow for a better understanding of how the observed data maps to physical properties and to better optimize the model libraries for a given set of observational data. Next, the SOMs are used to estimate the physical parameters of 14,000 z~1 galaxies in the COSMOS field and found to be in agreement with those measured with SED fitting. However, the SOM method is able to estimate the full probability distribution functions for each galaxy up to about a million times faster than direct model fitting. We conclude by discussing how this speed up and learning how the galaxy data manifold maps to physical parameter space and visualizing this mapping in lower dimensions helps overcome other challenges in galaxy formation and evolution.