Using Galaxy Evolution as Source of Physics-Based Ground Truth for Generative Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914864461512704 |
|---|---|
| author | Li, Yun Qi Do, Tuan Jones, Evan Boscoe, Bernie Alfaro, Kevin Nguyen, Zooey |
| author_facet | Li, Yun Qi Do, Tuan Jones, Evan Boscoe, Bernie Alfaro, Kevin Nguyen, Zooey |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_07229 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Using Galaxy Evolution as Source of Physics-Based Ground Truth for Generative Models Li, Yun Qi Do, Tuan Jones, Evan Boscoe, Bernie Alfaro, Kevin Nguyen, Zooey Instrumentation and Methods for Astrophysics Artificial Intelligence 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. |
| title | Using Galaxy Evolution as Source of Physics-Based Ground Truth for Generative Models |
| topic | Instrumentation and Methods for Astrophysics Artificial Intelligence |
| url | https://arxiv.org/abs/2407.07229 |