Machine Learning Applied to X-Ray Spectra: Separating Stars in Orion Nebula Cluster from Active Galactic Nuclei in CDFS
Modern X-ray telescopes have detected hundreds of thousands of X-ray sources in the universe. However, current methods to classify these sources using the X-ray data themselves suffer problems—detailed X-ray spectroscopy of individual sources is too time consuming, while hardness ratios often lack a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | The Astrophysical Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/1538-4357/acc39d |
| _version_ | 1797698898122244096 |
|---|---|
| author | Pavan R. Hebbar Craig O. Heinke |
| author_facet | Pavan R. Hebbar Craig O. Heinke |
| author_sort | Pavan R. Hebbar |
| collection | DOAJ |
| description | Modern X-ray telescopes have detected hundreds of thousands of X-ray sources in the universe. However, current methods to classify these sources using the X-ray data themselves suffer problems—detailed X-ray spectroscopy of individual sources is too time consuming, while hardness ratios often lack accuracy, and can be difficult to use effectively. These methods fail to use the power of X-ray CCD detectors to identify X-ray emission lines and distinguish line-dominated spectra (from chromospherically active stars, supernova remnants, etc.) from continuum-dominated ones (e.g., compact objects or active galactic nuclei, AGN). In this paper, we probe the use of artificial neural networks (ANN) in differentiating Chandra spectra of young stars in the Chandra Orion Ultradeep Project (COUP) survey from AGN in the Chandra Deep Field South (CDFS) survey. We use these surveys to generate 100,000 artificial spectra of stars and AGN, and train our ANN models to separate the two kinds of spectra. We find that our methods reach an accuracy of ∼92% in classifying simulated spectra of moderate-brightness objects in typical exposures, but their performance decreases on the observed COUP and CDFS spectra (∼91%), due in large part to the relatively high background of these long-exposure data sets. We also investigate the performance of our methods with changing properties of the spectra such as the net source counts, the relative contribution of background, the absorption column of the sources, etc. We conclude that these methods have substantial promise for application to large X-ray surveys. |
| first_indexed | 2024-03-12T04:00:43Z |
| format | Article |
| id | doaj.art-739de5eec96a4099b90dd050e827d5e1 |
| institution | Directory Open Access Journal |
| issn | 1538-4357 |
| language | English |
| last_indexed | 2024-03-12T04:00:43Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astrophysical Journal |
| spelling | doaj.art-739de5eec96a4099b90dd050e827d5e12023-09-03T11:34:57ZengIOP PublishingThe Astrophysical Journal1538-43572023-01-0194911210.3847/1538-4357/acc39dMachine Learning Applied to X-Ray Spectra: Separating Stars in Orion Nebula Cluster from Active Galactic Nuclei in CDFSPavan R. Hebbar0https://orcid.org/0000-0002-4961-4690Craig O. Heinke1https://orcid.org/0000-0003-3944-6109Department of Physics, CCIS 4-181, University of Alberta , Edmonton, AB T6G 2E1, Canada ; hebbar@ualberta.caDepartment of Physics, CCIS 4-181, University of Alberta , Edmonton, AB T6G 2E1, Canada ; hebbar@ualberta.caModern X-ray telescopes have detected hundreds of thousands of X-ray sources in the universe. However, current methods to classify these sources using the X-ray data themselves suffer problems—detailed X-ray spectroscopy of individual sources is too time consuming, while hardness ratios often lack accuracy, and can be difficult to use effectively. These methods fail to use the power of X-ray CCD detectors to identify X-ray emission lines and distinguish line-dominated spectra (from chromospherically active stars, supernova remnants, etc.) from continuum-dominated ones (e.g., compact objects or active galactic nuclei, AGN). In this paper, we probe the use of artificial neural networks (ANN) in differentiating Chandra spectra of young stars in the Chandra Orion Ultradeep Project (COUP) survey from AGN in the Chandra Deep Field South (CDFS) survey. We use these surveys to generate 100,000 artificial spectra of stars and AGN, and train our ANN models to separate the two kinds of spectra. We find that our methods reach an accuracy of ∼92% in classifying simulated spectra of moderate-brightness objects in typical exposures, but their performance decreases on the observed COUP and CDFS spectra (∼91%), due in large part to the relatively high background of these long-exposure data sets. We also investigate the performance of our methods with changing properties of the spectra such as the net source counts, the relative contribution of background, the absorption column of the sources, etc. We conclude that these methods have substantial promise for application to large X-ray surveys.https://doi.org/10.3847/1538-4357/acc39dX-ray surveysX-ray identificationX-ray starsX-ray active galactic nucleiNeural networks |
| spellingShingle | Pavan R. Hebbar Craig O. Heinke Machine Learning Applied to X-Ray Spectra: Separating Stars in Orion Nebula Cluster from Active Galactic Nuclei in CDFS The Astrophysical Journal X-ray surveys X-ray identification X-ray stars X-ray active galactic nuclei Neural networks |
| title | Machine Learning Applied to X-Ray Spectra: Separating Stars in Orion Nebula Cluster from Active Galactic Nuclei in CDFS |
| title_full | Machine Learning Applied to X-Ray Spectra: Separating Stars in Orion Nebula Cluster from Active Galactic Nuclei in CDFS |
| title_fullStr | Machine Learning Applied to X-Ray Spectra: Separating Stars in Orion Nebula Cluster from Active Galactic Nuclei in CDFS |
| title_full_unstemmed | Machine Learning Applied to X-Ray Spectra: Separating Stars in Orion Nebula Cluster from Active Galactic Nuclei in CDFS |
| title_short | Machine Learning Applied to X-Ray Spectra: Separating Stars in Orion Nebula Cluster from Active Galactic Nuclei in CDFS |
| title_sort | machine learning applied to x ray spectra separating stars in orion nebula cluster from active galactic nuclei in cdfs |
| topic | X-ray surveys X-ray identification X-ray stars X-ray active galactic nuclei Neural networks |
| url | https://doi.org/10.3847/1538-4357/acc39d |
| work_keys_str_mv | AT pavanrhebbar machinelearningappliedtoxrayspectraseparatingstarsinorionnebulaclusterfromactivegalacticnucleiincdfs AT craigoheinke machinelearningappliedtoxrayspectraseparatingstarsinorionnebulaclusterfromactivegalacticnucleiincdfs |