2019/06/22 by Sandra Robles, Robles, Sandra, Jonathan S. Gómez +11
Computer Science · Mathematics · Physics and Astronomy · #Advanced Vision and Imaging #Astronomy and Astrophysical Research #Astrophysics of Galaxies (astro-ph.GA) #Cosmology and Nongalactic Astrophysics (astro-ph.CO) #FOS: Computer and information sciences #FOS: Physical sciences #Galaxies: Formation, Evolution, Phenomena #Machine Learning (cs.LG) #Machine Learning (stat.ML) #astro-ph.CO #astro-ph.GA #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1906.09382
11 pages, 7 figures, 2 tables, 3 appendices. Presented at the ICML 2019 Workshop on Theoretical Physics for Deep Learning
arxiv created 2019/06/22 · openalex publication_date 2019/06/22 · arxiv updated 2019/06/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Semi-analytic models are best suited to compare galaxy formation and evolution theories with observations. These models rely heavily on halo merger trees, and their realistic features (i.e., no drastic changes on halo mass or jumps on physical locations). Our aim is to provide a new framework for halo merger tree generation that takes advantage of the results of large volume simulations, with a modest computational cost. We treat halo merger tree construction as a matrix generation problem, and propose a Generative Adversarial Network that learns to generate realistic halo merger trees. We evaluate our proposal on merger trees from the EAGLE simulation suite, and show the quality of the generated trees.