Automatic spectral classification of stellar spectra with low signal-to-noise ratio using artificial neural networks

Navarro, S. G.; Corradi, R. L. M.; Mampaso, A.

doi:10.1051/0004-6361/201016422

Cited by 34 publications

(29 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bailer-Jones et al (1998) use a committee of neural networks and obtain 2.09 subclass error in the classification mode. Navarro et al (2012) set-up a two-stage classification system which is trained on spectral indices and outputs the spectral and luminosity class. Three networks in the first stage contain two hidden layers with 50 neurons in each layer.…”

Section: Classification Methodologymentioning

confidence: 99%

Application of convolutional neural networks for stellar spectral classification

Sharma

Kembhavi

et al. 2019

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

Due to the ever-expanding volume of observed spectroscopic data from surveys such as SDSS and LAMOST, it has become important to apply artificial intelligence (AI) techniques for analysing stellar spectra to solve spectral classification and regression problems like the determination of stellar atmospheric parameters T eff , log g, and [Fe/H]. We propose an automated approach for the classification of stellar spectra in the optical region using Convolutional Neural Networks. Traditional machine learning (ML) methods with "shallow" architecture (usually up to 2 hidden layers) have been trained for these purposes in the past. However, deep learning methods with a larger number of hidden layers allow the use of finer details in the spectrum which results in improved accuracy and better generalisation. Studying finer spectral signatures also enables us to determine accurate differential stellar parameters and find rare objects. We examine various machine and deep learning algorithms like Artificial Neural Networks (ANN), Random Forest (RF), and Convolutional Neural Network (CNN) to classify stellar spectra using the Jacoby Atlas, ELODIE and MILES spectral libraries as training samples. We test the performance of the trained networks on the Indo-U.S. Library of Coudé Feed Stellar Spectra (CFLIB). We show that using convolutional neural networks, we are able to lower the error up to 1.23 spectral sub-classes as compared to that of 2 sub-classes achieved in the past studies with ML approach. We further apply the trained model to classify stellar spectra retrieved from the SDSS database with SNR>20.

show abstract

Section: Classification Methodologymentioning

confidence: 99%

Application of convolutional neural networks for stellar spectral classification

Sharma

Kembhavi

et al. 2019

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

show abstract

“…e automatic stellar spectral classification of big astronomical databases is a challenge that has been addressed by computational intelligence techniques; among them the Artificial Neural Networks (ANNs) have proven their effectiveness and accuracy [4][5][6][7][8][9][10]. Results found in the studies mentioned previously showed that, with the Artificial Neural Network approach, it is possible to classify spectra with S : N as low as 20 with errors in the classification process lower than 2 spectral subtypes; therefore, with the advent of massive astronomical databases, the automatic methods are clearly more necessary to extract and analyze the spectral information in a fast and accurate way, even when noise is a strong characteristic in the data.…”

Section: Introductionmentioning

confidence: 99%

“…Some of the most powerful advantages of ANNs are their capacity to handle large volumes of information, resistance to noise in the data as well as to the lack of data, and the capacity to reach an accuracy on the classification process similar to that of an expert [9]. Combined with the use of Artificial Neural Networks and other classifiers, dimensionality reduction methods as Principal Component Analysis (PCA), Isomap, and index measurement have been applied, in order to reduce the size of the input vector and extract the main features for classification [8,10,16]; in these works, the authors reported that dimensionality reduction methods are efficient to extract and retain the most useful information in the spectra and thus can be used in the classification process.…”

Section: Introductionmentioning

confidence: 99%

Application of Artificial Neural Networks for the Automatic Spectral Classification

Vilavicencio-Arcadia

Navarro

Corral

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Classification in astrophysics is a fundamental process, especially when it is necessary to understand several aspects of the evolution and distribution of the objects. Over an astronomical image, we need to discern between stars and galaxies and to determine the morphological type for each galaxy. The spectral classification of stars provides important information about stellar physical parameters like temperature and allows us to determine their distance; with this information, it is possible to evaluate other parameters like their physical size and the real 3D distribution of each type of objects. In this work, we present the application of two Artificial Intelligence (AI) techniques for the automatic spectral classification of stellar spectra obtained from the first data release of LAMOST and also to the more recent release (DR5). Two types of Artificial Neural Networks were selected: a feedforward neural network trained according to the Levenberg–Marquardt Optimization Algorithm (LMA) and a Generalized Regression Neural Network (GRNN). During the study, we used four datasets: the first was obtained from the LAMOST first data release and consisted of 50731 spectra with signal-to-noise ratio above 20, the second dataset was obtained from the Indo-US spectral database (1273 spectra), the third one (the STELIB spectral database) was used as an independent test dataset, and the fourth dataset was obtained from LAMOST DR5 and consisted of 17990 stellar spectra with signal-to-noise ratio above 20 also. The results in the first part of the work, when the autoconsistency of the DR1 data was probed, showed some problems in the spectral classification available in LAMOST DR1. In order to accomplish a better classification, we made a two-step process: first the LAMOST and STELIB datasets were classified by the two IA techniques trained with the entire Indo-US dataset. The resulted classification allows us to discriminate at least three groups: the first group contained O and B type stars, whereas the second contained A, F, and G type stars, and finally, the third group contained K and M type stars. The second step consisted of a refinement of the classification, but this time for every group, the most relevant indices were selected. We compared the accuracy reached by the two techniques when they are trained and tested using LAMOST spectra and their published classification and the resultant classifications obtained with the ANNs trained with the Indo-US dataset and applied over the STELIB and LAMOST spectra. Finally, in the first part, we compared the LAMOST DR1 classification with the classification obtained by the application of the NNs GRNNs and LMA trained with the Indo-US dataset. In the second part of the paper, we analyze a set of 17990 stellar spectra from LAMOST DR5 and the very significant improvement in the spectral classification available in DR5 database was verified. For this, we trained ANNs using the k-fold cross-validation technique with k = 5.

show abstract

“…Spectral Classification: In order to determine an accurate spectral classification of the stars near the line of sight of each of the PNe, we obtained the spectra of these stars at the WHT, using the LDSS2 multi-object spectrograph with a resolution of 6Å. To determine the spectral type of the stars in each field, we developed an Artificial Neural Network System which is able to classify spectra with signal to noise ratio (S/N) as low as 20 with an accuracy better than 2 spectral subtypes (Navarro 2005;Navarro et al 2011). The neural networks were trained with the measurement of 35 spectral lines that are sensitive to spectral type and luminosity class.…”

Section: Observationsmentioning

confidence: 99%

Distance determination to PNe using the extinction-distance method

2011

View full text Add to dashboard Cite

Abstract. We present individual distances to three PNe: NGC 6537, NGC 6781 and NGC 7027, determined by the extinction-distance method. These objects are part of a larger sample (35) of PNe that we observed at ORM. In order to apply this method, and to obtain accurate distances, we determined the spectral type of 40 to 60 stars in the line of sight of each PNe. This implied the necessity of classifying few thousands of stellar spectra with S/N ratio between 10 and 60. To solve such need we developed an ANN system to perform automatic spectral classification which could classify spectra with S/N ratio as low as 20 with an accuracy better than 2 spectral subtypes. In this poster we compare the accuracy of such distances with previous distance determinations using other methods. We conclude that it is possible to use this method to obtain the distance of a large number of PNe with better precision.

show abstract

Automatic spectral classification of stellar spectra with low signal-to-noise ratio using artificial neural networks

Cited by 34 publications

References 30 publications

Application of convolutional neural networks for stellar spectral classification

Application of convolutional neural networks for stellar spectral classification

Application of Artificial Neural Networks for the Automatic Spectral Classification

Distance determination to PNe using the extinction-distance method

Contact Info

Product

Resources

About