Spectra-GANs: A New Automated Denoising Method for Low-S/N Stellar Spectra
Numerous spectra can be obtained from sky surveys such as the Sloan Digital Sky Survey and the Large Sky Area Multi-Object Fibre Spectroscopic Telescope. However, a considerable fraction of such spectra, which are also valuable for astronomical research, are of low quality, possessing characteristic...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9109312/ |
| _version_ | 1818624145641963520 |
|---|---|
| author | Minglei Wu Yude Bu Jingchang Pan Zhenping Yi Xiaoming Kong |
| author_facet | Minglei Wu Yude Bu Jingchang Pan Zhenping Yi Xiaoming Kong |
| author_sort | Minglei Wu |
| collection | DOAJ |
| description | Numerous spectra can be obtained from sky surveys such as the Sloan Digital Sky Survey and the Large Sky Area Multi-Object Fibre Spectroscopic Telescope. However, a considerable fraction of such spectra, which are also valuable for astronomical research, are of low quality, possessing characteristics such as low signal-to-noise ratio (low-S/N). Principal component analysis is widely used to process these low-S/N spectra, but it is not efficient enough to describe the non-linear properties within the spectra. Wavelets are often used to denoise the low-S/N spectra. However, as is well known, the most optimal wavelet basis for each type of spectra needs to be determined; therefore, wavelet analysis is very difficult to use in practice. Restricted Boltzmann machine is a non-linear algorithm that performs poorly when applied to low-S/N spectra. Denoising Convolutional Neural Networks (DnCNN) is a promising denoiser, however, its performance is unsatisfactory due to the lack of suitable noise model. To better exploit the spectra with low-S/N, we propose a new method that can be used to obtain better denoised spectra when compared to those obtained using other methods. A new method called the Spectra Generative Adversarial Nets (Spectra-GANs) is introduced. Spectra-GANs is simply a feedforward neural network that learns the difference between the input vector and the target by minimizing the loss function. It can be used in spectral denoising. The performance of Spectra-GANs is better than those of other methods with regard to denoising the spectra, especially with regard to extremely low-S/N spectral processing. Thus, Spectra-GANs proposed herein is a suitable alternative to previously used methods in spectral denoising. |
| first_indexed | 2024-12-16T18:52:18Z |
| format | Article |
| id | doaj.art-f2168c52cc66405c9c3a6649626af074 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T18:52:18Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f2168c52cc66405c9c3a6649626af0742022-12-21T22:20:40ZengIEEEIEEE Access2169-35362020-01-01810791210792610.1109/ACCESS.2020.30001749109312Spectra-GANs: A New Automated Denoising Method for Low-S/N Stellar SpectraMinglei Wu0https://orcid.org/0000-0002-1801-6591Yude Bu1https://orcid.org/0000-0002-9474-4734Jingchang Pan2https://orcid.org/0000-0002-3064-7708Zhenping Yi3https://orcid.org/0000-0001-8590-4110Xiaoming Kong4https://orcid.org/0000-0002-4764-4749School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, ChinaSchool of Mathematics and Statistics, Shandong University, Weihai, ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, ChinaNumerous spectra can be obtained from sky surveys such as the Sloan Digital Sky Survey and the Large Sky Area Multi-Object Fibre Spectroscopic Telescope. However, a considerable fraction of such spectra, which are also valuable for astronomical research, are of low quality, possessing characteristics such as low signal-to-noise ratio (low-S/N). Principal component analysis is widely used to process these low-S/N spectra, but it is not efficient enough to describe the non-linear properties within the spectra. Wavelets are often used to denoise the low-S/N spectra. However, as is well known, the most optimal wavelet basis for each type of spectra needs to be determined; therefore, wavelet analysis is very difficult to use in practice. Restricted Boltzmann machine is a non-linear algorithm that performs poorly when applied to low-S/N spectra. Denoising Convolutional Neural Networks (DnCNN) is a promising denoiser, however, its performance is unsatisfactory due to the lack of suitable noise model. To better exploit the spectra with low-S/N, we propose a new method that can be used to obtain better denoised spectra when compared to those obtained using other methods. A new method called the Spectra Generative Adversarial Nets (Spectra-GANs) is introduced. Spectra-GANs is simply a feedforward neural network that learns the difference between the input vector and the target by minimizing the loss function. It can be used in spectral denoising. The performance of Spectra-GANs is better than those of other methods with regard to denoising the spectra, especially with regard to extremely low-S/N spectral processing. Thus, Spectra-GANs proposed herein is a suitable alternative to previously used methods in spectral denoising.https://ieeexplore.ieee.org/document/9109312/Stellar spectramachine learningdenoising |
| spellingShingle | Minglei Wu Yude Bu Jingchang Pan Zhenping Yi Xiaoming Kong Spectra-GANs: A New Automated Denoising Method for Low-S/N Stellar Spectra IEEE Access Stellar spectra machine learning denoising |
| title | Spectra-GANs: A New Automated Denoising Method for Low-S/N Stellar Spectra |
| title_full | Spectra-GANs: A New Automated Denoising Method for Low-S/N Stellar Spectra |
| title_fullStr | Spectra-GANs: A New Automated Denoising Method for Low-S/N Stellar Spectra |
| title_full_unstemmed | Spectra-GANs: A New Automated Denoising Method for Low-S/N Stellar Spectra |
| title_short | Spectra-GANs: A New Automated Denoising Method for Low-S/N Stellar Spectra |
| title_sort | spectra gans a new automated denoising method for low s n stellar spectra |
| topic | Stellar spectra machine learning denoising |
| url | https://ieeexplore.ieee.org/document/9109312/ |
| work_keys_str_mv | AT mingleiwu spectragansanewautomateddenoisingmethodforlowsnstellarspectra AT yudebu spectragansanewautomateddenoisingmethodforlowsnstellarspectra AT jingchangpan spectragansanewautomateddenoisingmethodforlowsnstellarspectra AT zhenpingyi spectragansanewautomateddenoisingmethodforlowsnstellarspectra AT xiaomingkong spectragansanewautomateddenoisingmethodforlowsnstellarspectra |