Andres C. Rodríguez, Tomasz Kacprzak, Aurelien Lucchi, Adam Amara, Raphaël Sgier, Janis Fluri, Thomas Hofmann, Alexandre Réfrégier
{"title":"Fast cosmic web simulations with generative adversarial networks","authors":"Andres C. Rodríguez, Tomasz Kacprzak, Aurelien Lucchi, Adam Amara, Raphaël Sgier, Janis Fluri, Thomas Hofmann, Alexandre Réfrégier","doi":"10.1186/s40668-018-0026-4","DOIUrl":null,"url":null,"abstract":"<p>Dark matter in the universe evolves through gravity to form a complex network of halos, filaments, sheets and voids, that is known as the cosmic web. Computational models of the underlying physical processes, such as classical N-body simulations, are extremely resource intensive, as they track the action of gravity in an expanding universe using billions of particles as tracers of the cosmic matter distribution. Therefore, upcoming cosmology experiments will face a computational bottleneck that may limit the exploitation of their full scientific potential. To address this challenge, we demonstrate the application of a machine learning technique called Generative Adversarial Networks (GAN) to learn models that can efficiently generate new, physically realistic realizations of the cosmic web. Our training set is a small, representative sample of 2D image snapshots from N-body simulations of size 500 and 100 Mpc. We show that the GAN-generated samples are qualitatively and quantitatively very similar to the originals. For the larger boxes of size 500 Mpc, it is very difficult to distinguish them visually. The agreement of the power spectrum <span>\\(P_{k}\\)</span> is 1–2% for most of the range, between <span>\\(k=0.06\\)</span> and <span>\\(k=0.4\\)</span>. For the remaining values of <i>k</i>, the agreement is within 15%, with the error rate increasing for <span>\\(k>0.8\\)</span>. For smaller boxes of size 100 Mpc, we find that the visual agreement to be good, but some differences are noticable. The error on the power spectrum is of the order of 20%. We attribute this loss of performance to the fact that the matter distribution in 100 Mpc cutouts was very inhomogeneous between images, a situation in which the performance of GANs is known to deteriorate. We find a good match for the correlation matrix of full <span>\\(P_{k}\\)</span> range for 100 Mpc data and of small scales for 500 Mpc, with ~20% disagreement for large scales. An important advantage of generating cosmic web realizations with a GAN is the considerable gains in terms of computation time. Each new sample generated by a GAN takes a fraction of a second, compared to the many hours needed by traditional N-body techniques. We anticipate that the use of generative models such as GANs will therefore play an important role in providing extremely fast and precise simulations of cosmic web in the era of large cosmological surveys, such as Euclid and Large Synoptic Survey Telescope (LSST).</p>","PeriodicalId":523,"journal":{"name":"Computational Astrophysics and Cosmology","volume":null,"pages":null},"PeriodicalIF":16.2810,"publicationDate":"2018-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1186/s40668-018-0026-4","citationCount":"76","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computational Astrophysics and Cosmology","FirstCategoryId":"4","ListUrlMain":"https://link.springer.com/article/10.1186/s40668-018-0026-4","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 76
Abstract
Dark matter in the universe evolves through gravity to form a complex network of halos, filaments, sheets and voids, that is known as the cosmic web. Computational models of the underlying physical processes, such as classical N-body simulations, are extremely resource intensive, as they track the action of gravity in an expanding universe using billions of particles as tracers of the cosmic matter distribution. Therefore, upcoming cosmology experiments will face a computational bottleneck that may limit the exploitation of their full scientific potential. To address this challenge, we demonstrate the application of a machine learning technique called Generative Adversarial Networks (GAN) to learn models that can efficiently generate new, physically realistic realizations of the cosmic web. Our training set is a small, representative sample of 2D image snapshots from N-body simulations of size 500 and 100 Mpc. We show that the GAN-generated samples are qualitatively and quantitatively very similar to the originals. For the larger boxes of size 500 Mpc, it is very difficult to distinguish them visually. The agreement of the power spectrum \(P_{k}\) is 1–2% for most of the range, between \(k=0.06\) and \(k=0.4\). For the remaining values of k, the agreement is within 15%, with the error rate increasing for \(k>0.8\). For smaller boxes of size 100 Mpc, we find that the visual agreement to be good, but some differences are noticable. The error on the power spectrum is of the order of 20%. We attribute this loss of performance to the fact that the matter distribution in 100 Mpc cutouts was very inhomogeneous between images, a situation in which the performance of GANs is known to deteriorate. We find a good match for the correlation matrix of full \(P_{k}\) range for 100 Mpc data and of small scales for 500 Mpc, with ~20% disagreement for large scales. An important advantage of generating cosmic web realizations with a GAN is the considerable gains in terms of computation time. Each new sample generated by a GAN takes a fraction of a second, compared to the many hours needed by traditional N-body techniques. We anticipate that the use of generative models such as GANs will therefore play an important role in providing extremely fast and precise simulations of cosmic web in the era of large cosmological surveys, such as Euclid and Large Synoptic Survey Telescope (LSST).
宇宙中的暗物质通过引力演化,形成了一个由光晕、细丝、薄片和空洞组成的复杂网络,这就是我们所知的宇宙网。基础物理过程的计算模型,如经典的n体模拟,是极其资源密集型的,因为它们使用数十亿粒子作为宇宙物质分布的示踪剂来跟踪膨胀宇宙中的重力作用。因此,即将到来的宇宙学实验将面临计算瓶颈,这可能会限制其充分发挥科学潜力。为了应对这一挑战,我们展示了一种称为生成对抗网络(GAN)的机器学习技术的应用,以学习能够有效地生成新的、物理上真实的宇宙网实现的模型。我们的训练集是来自大小为500和100 Mpc的n个体模拟的2D图像快照的小型代表性样本。结果表明,gan生成的样品在定性和定量上与原始样品非常相似。对于500mpc的大盒子,很难在视觉上区分它们。功率谱\(P_{k}\)的一致性为1-2% for most of the range, between \(k=0.06\) and \(k=0.4\). For the remaining values of k, the agreement is within 15%, with the error rate increasing for \(k>0.8\). For smaller boxes of size 100 Mpc, we find that the visual agreement to be good, but some differences are noticable. The error on the power spectrum is of the order of 20%. We attribute this loss of performance to the fact that the matter distribution in 100 Mpc cutouts was very inhomogeneous between images, a situation in which the performance of GANs is known to deteriorate. We find a good match for the correlation matrix of full \(P_{k}\) range for 100 Mpc data and of small scales for 500 Mpc, with ~20% disagreement for large scales. An important advantage of generating cosmic web realizations with a GAN is the considerable gains in terms of computation time. Each new sample generated by a GAN takes a fraction of a second, compared to the many hours needed by traditional N-body techniques. We anticipate that the use of generative models such as GANs will therefore play an important role in providing extremely fast and precise simulations of cosmic web in the era of large cosmological surveys, such as Euclid and Large Synoptic Survey Telescope (LSST).
期刊介绍:
Computational Astrophysics and Cosmology (CompAC) is now closed and no longer accepting submissions. However, we would like to assure you that Springer will maintain an archive of all articles published in CompAC, ensuring their accessibility through SpringerLink's comprehensive search functionality.