Galaxy mergers play an important role in the formation and evolution of galaxies. However, identifying mergers can be difficult, especially at high redshift, due to effects such as: cosmological surface brightness dimming, poor resolution of images, the shifting of optical light to the infrared, and the inherently more irregular morphologies of younger galaxies. The advent of JWST and new deep, high-resolution near-infrared NIRCam images from the Cosmic Evolution Early Release Science Survey (CEERS) will help mitigate some of these problems to better detect high redshift merger features. Simultaneously, sophisticated machine learning analysis techniques have the po- tential to more accurately identify mergers by exploiting complex multidimensional data (whether directly from multi-band images or from pre-computed quantitative measurements). In this dissertation, we investigate the use of machine learning techniques (random forests and convolutional neural networks) to identify high redshift galaxy mergers. We create simulated JWST CEERS NIRCam images in six filters and HST CANDELS/Wide WFC3/ACS images in four filters from IllustrisTNG and the Santa Cruz SAM. We use these simulated data to train the algorithms. We calculate morphology parameters for galaxies in those images using Galapagos-2 and statmorph, which are used as inputs for the random forests. We also cut stamps of uniform size for those galaxies, which are used as inputs to the convolutional neural networks. The input labels for the simulated galaxies were derived from Illustris merger history catalogs, such that “mergers” are galaxies that have experienced or will experience a merger within ±250 Myr and “non-mergers” are those that will not experience a merger within that time frame. We train random forests on simulated CEERS galaxies from 0.5 < z < 5 and on simulated CANDELS galaxies from 1 < z < 3. We train convolutional neural network on on simulated CEERS galaxies from 3 < z < 5 and on simulated CANDELS galaxies from 1 < z < 3. We then apply our models to observed CEERS galaxies at 3 < z < 5 and observed CANDELS galaxies at 1 < z < 3 and compare with visual classifications. We find that our models correctly classify ∼ 60 − 70% of simulated mergers and non-mergers. Our models outperform random classifiers as well as classic methods of selecting mergers using morphology parameters such as G − M20. When applied to observed galaxies, our models do not perform as well. We investigate what features the models find most useful, as well as characteristics of false positives and false negatives. We also calculate merger rates derived from the identifications made by the models, and find that our merger rates generally agree with previous literature.

Library of Congress Subject Headings

Galaxy mergers; Red shift; Machine learning

Publication Date


Document Type


Student Type


Degree Name

Astrophysical Sciences and Technology (Ph.D.)

Department, Program, or Center

School of Physics and Astronomy (COS)


Jeyhan Kartaltepe

Advisor/Committee Member

Nathan Cahill

Advisor/Committee Member

Amber Straughn


RIT – Main Campus

Plan Codes