Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914145675247616 |
|---|---|
| author | Shen, Jeff Lanusse, Francois Parker, Liam Holden Liu, Ollie Hehir, Tom Sarra, Leopoldo Meyer, Lucas Bowles, Micah Wagner-Carena, Sebastian Wagner-Carena, Sebastian Qu, Helen Golkar, Siavash Bietti, Alberto Bourfoune, Hatim Cassereau, Nathan Cornette, Pierre Hirashima, Keiya Krawezik, Geraud Ohana, Ruben Lourie, Nicholas McCabe, Michael Morel, Rudy Mukhopadhyay, Payel Pettee, Mariel Blancard, Bruno Régaldo-Saint Cho, Kyunghyun Cranmer, Miles Ho, Shirley |
| author_facet | Shen, Jeff Lanusse, Francois Parker, Liam Holden Liu, Ollie Hehir, Tom Sarra, Leopoldo Meyer, Lucas Bowles, Micah Wagner-Carena, Sebastian Wagner-Carena, Sebastian Qu, Helen Golkar, Siavash Bietti, Alberto Bourfoune, Hatim Cassereau, Nathan Cornette, Pierre Hirashima, Keiya Krawezik, Geraud Ohana, Ruben Lourie, Nicholas McCabe, Michael Morel, Rudy Mukhopadhyay, Payel Pettee, Mariel Blancard, Bruno Régaldo-Saint Cho, Kyunghyun Cranmer, Miles Ho, Shirley |
| contents | Sequential scientific data span many resolutions and domains, and unifying them into a common representation is a key step toward developing foundation models for the sciences. Astronomical spectra exemplify this challenge: massive surveys have collected millions of spectra across a wide range of wavelengths and resolutions, yet analyses remain fragmented across spectral domains (e.g., optical vs. infrared) and object types (e.g., stars vs. galaxies), limiting the ability to pool information across datasets. We present a deep learning model that jointly learns from heterogeneous spectra in a self-supervised manner. Our universal spectral tokenizer processes spectra from a variety of object types and resolutions directly on their native wavelength grids, producing intrinsically aligned, homogeneous, and physically meaningful representations that can be efficiently adapted to achieve competitive performance across a range of downstream tasks. For the first time, we demonstrate that a single model can unify spectral data across resolutions and domains, suggesting that our model can serve as a powerful building block for foundation models in astronomy -- and potentially extend to other scientific domains with heterogeneous sequential data, such as climate and healthcare. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17959 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning Shen, Jeff Lanusse, Francois Parker, Liam Holden Liu, Ollie Hehir, Tom Sarra, Leopoldo Meyer, Lucas Bowles, Micah Wagner-Carena, Sebastian Wagner-Carena, Sebastian Qu, Helen Golkar, Siavash Bietti, Alberto Bourfoune, Hatim Cassereau, Nathan Cornette, Pierre Hirashima, Keiya Krawezik, Geraud Ohana, Ruben Lourie, Nicholas McCabe, Michael Morel, Rudy Mukhopadhyay, Payel Pettee, Mariel Blancard, Bruno Régaldo-Saint Cho, Kyunghyun Cranmer, Miles Ho, Shirley Instrumentation and Methods for Astrophysics Artificial Intelligence Machine Learning Sequential scientific data span many resolutions and domains, and unifying them into a common representation is a key step toward developing foundation models for the sciences. Astronomical spectra exemplify this challenge: massive surveys have collected millions of spectra across a wide range of wavelengths and resolutions, yet analyses remain fragmented across spectral domains (e.g., optical vs. infrared) and object types (e.g., stars vs. galaxies), limiting the ability to pool information across datasets. We present a deep learning model that jointly learns from heterogeneous spectra in a self-supervised manner. Our universal spectral tokenizer processes spectra from a variety of object types and resolutions directly on their native wavelength grids, producing intrinsically aligned, homogeneous, and physically meaningful representations that can be efficiently adapted to achieve competitive performance across a range of downstream tasks. For the first time, we demonstrate that a single model can unify spectral data across resolutions and domains, suggesting that our model can serve as a powerful building block for foundation models in astronomy -- and potentially extend to other scientific domains with heterogeneous sequential data, such as climate and healthcare. |
| title | Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning |
| topic | Instrumentation and Methods for Astrophysics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.17959 |