Can Self-Organizing Maps accurately predict photometric redshifts?

TL;DR

This paper explores using Self-Organizing Maps, an unsupervised machine learning technique, to estimate photometric redshifts, showing competitive accuracy compared to other methods across various astronomical datasets.

Contribution

It introduces a novel application of Self-Organizing Maps for photometric redshift estimation and evaluates its performance against established approaches.

Findings

SOM achieved RMSE of 0.023 for Main Galaxy Sample

SOM outlier percentages are competitive with other methods

Further research needed for more robust SOM-based estimates

Abstract

We present an unsupervised machine learning approach that can be employed for estimating photometric redshifts. The proposed method is based on a vector quantization approach called Self--Organizing Mapping (SOM). A variety of photometrically derived input values were utilized from the Sloan Digital Sky Survey's Main Galaxy Sample, Luminous Red Galaxy, and Quasar samples along with the PHAT0 data set from the PHoto-z Accuracy Testing project. Regression results obtained with this new approach were evaluated in terms of root mean square error (RMSE) to estimate the accuracy of the photometric redshift estimates. The results demonstrate competitive RMSE and outlier percentages when compared with several other popular approaches such as Artificial Neural Networks and Gaussian Process Regression. SOM RMSE--results (using $\Delta$z=z$_{phot}$--z$_{spec}$) for the Main Galaxy Sample are 0.023, for the Luminous Red Galaxy sample 0.027, Quasars are 0.418, and PHAT0 synthetic data are 0.022. The results demonstrate that there are non--unique solutions for estimating SOM RMSEs. Further research is needed in order to find more robust estimation techniques using SOMs, but the results herein are a positive indication of their capabilities when compared with other well-known methods.