Using Galaxy Evolution as Source of Physics-Based Ground Truth for Generative Models

• URL: http://arxiv.org/abs/2407.07229v1
• Date: Tue, 9 Jul 2024 21:01:08 GMT
• Title: Using Galaxy Evolution as Source of Physics-Based Ground Truth for Generative Models
• Authors: Yun Qi Li, Tuan Do, Evan Jones, Bernie Boscoe, Kevin Alfaro, Zooey Nguyen,
• Abstract summary: We build a conditional denoising diffusionaxy probabilistic model (DDPM) and a conditional variational autoencoder (CVAE) This is one of the first studies to probe these generative models using physically motivated metrics. We find that both models produce comparable realistic galaxies based on human evaluation, but our physics-based metrics are better able to discern the strengths and weaknesses of the generative models.
• Score: 0.9701233658865522
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative models producing images have enormous potential to advance discoveries across scientific fields and require metrics capable of quantifying the high dimensional output. We propose that astrophysics data, such as galaxy images, can test generative models with additional physics-motivated ground truths in addition to human judgment. For example, galaxies in the Universe form and change over billions of years, following physical laws and relationships that are both easy to characterize and difficult to encode in generative models. We build a conditional denoising diffusion probabilistic model (DDPM) and a conditional variational autoencoder (CVAE) and test their ability to generate realistic galaxies conditioned on their redshifts (galaxy ages). This is one of the first studies to probe these generative models using physically motivated metrics. We find that both models produce comparable realistic galaxies based on human evaluation, but our physics-based metrics are better able to discern the strengths and weaknesses of the generative models. Overall, the DDPM model performs better than the CVAE on the majority of the physics-based metrics. Ultimately, if we can show that generative models can learn the physics of galaxy evolution, they have the potential to unlock new astrophysical discoveries.

Related papers

• How Far is Video Generation from World Model: A Physical Law Perspective [101.24278831609249]
  OpenAI's Sora highlights the potential of video generation for developing world models that adhere to physical laws. But the ability of video generation models to discover such laws purely from visual data without human priors can be questioned. In this work, we evaluate across three key scenarios: in-distribution, out-of-distribution, and generalization.
  arXiv  Detail & Related papers  (2024-11-04T18:53:05Z)
• Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation [51.750634349748736]
  Text-to-video (T2V) models have made significant strides in visualizing complex prompts. However, the capacity of these models to accurately represent intuitive physics remains largely unexplored. We introduce PhyGenBench to evaluate physical commonsense correctness in T2V generation.
  arXiv  Detail & Related papers  (2024-10-07T17:56:04Z)
• VideoPhy: Evaluating Physical Commonsense for Video Generation [93.28748850301949]
  We present VideoPhy, a benchmark designed to assess whether the generated videos follow physical commonsense for real-world activities. We then generate videos conditioned on captions from diverse state-of-the-art text-to-video generative models. Our human evaluation reveals that the existing models severely lack the ability to generate videos adhering to the given text prompts.
  arXiv  Detail & Related papers  (2024-06-05T17:53:55Z)
• Can AI Understand Our Universe? Test of Fine-Tuning GPT by Astrophysical Data [6.0108108767559525]
  ChatGPT is the most talked-about concept in recent months, captivating both professionals and the general public alike. In this article, we fine-tune the generative pre-trained transformer (GPT) model by the astronomical data from the observations of galaxies, quasars, stars, gamma-ray bursts (GRBs) and simulations of black holes (BHs) We regard this as a successful test, marking the LLM's proven efficacy in scientific research.
  arXiv  Detail & Related papers  (2024-04-14T20:52:19Z)
• Towards solving model bias in cosmic shear forward modeling [2.967246997200238]
  Weak gravitational lensing generates a slight shearing of galaxy morphologies called cosmic shear. Modern techniques of shear estimation based on statistics of ellipticity measurements suffer from the fact that the ellipticity is not a well-defined quantity for arbitrary galaxy light profiles. We show that a hybrid physical and deep learning Hierarchical Bayesian Model, where a generative model captures the galaxy morphology, enables us to recover an unbiased estimate of the shear on realistic galaxies.
  arXiv  Detail & Related papers  (2022-10-28T16:23:49Z)
• Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One [83.5162421521224]
  We propose a unique method termed E-ARM for training autoregressive generative models. E-ARM takes advantage of a well-designed energy-based learning objective. We show that E-ARM can be trained efficiently and is capable of alleviating the exposure bias problem.
  arXiv  Detail & Related papers  (2022-06-26T10:58:41Z)
• Learning cosmology and clustering with cosmic graphs [0.0]
  We train deep learning models on thousands of galaxy catalogues from the state-of-the-art hydrodynamic simulations of the CAMELS project. We first show that GNNs can learn to compute the power spectrum of galaxy catalogues with a few percent accuracy. We then train GNNs to perform likelihood-free inference at the galaxy-field level.
  arXiv  Detail & Related papers  (2022-04-28T18:00:02Z)
• Which priors matter? Benchmarking models for learning latent dynamics [70.88999063639146]
  Several methods have proposed to integrate priors from classical mechanics into machine learning models. We take a sober look at the current capabilities of these models. We find that the use of continuous and time-reversible dynamics benefits models of all classes.
  arXiv  Detail & Related papers  (2021-11-09T23:48:21Z)
• Realistic galaxy image simulation via score-based generative models [0.0]
  We show that a score-based generative model can be used to produce realistic yet fake images that mimic observations of galaxies. Subjectively, the generated galaxies are highly realistic when compared with samples from the real dataset.
  arXiv  Detail & Related papers  (2021-11-02T16:27:08Z)
• Machine Learning for Discovering Effective Interaction Kernels between Celestial Bodies from Ephemerides [10.77689830299308]
  We use a data-driven learning approach to derive a stable and accurate model for the motion of celestial bodies in our Solar System. By modeling the major astronomical bodies in the Solar System as pairwise interacting agents, our learned model generate extremely accurate dynamics. Our model can provide a unified explanation to the observation data, especially in terms of reproducing the perihelion precession of Mars, Mercury, and the Moon.
  arXiv  Detail & Related papers  (2021-08-26T16:30:59Z)
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling [86.9726984929758]
  We focus on the integration of incomplete physics models into deep generative models. We propose a VAE architecture in which a part of the latent space is grounded by physics. We demonstrate generative performance improvements over a set of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-02-25T20:28:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.