More Efficient and Reliable: Identifying RRab Stars with Blazhko Effect by Deep Convolutional Neural Network
The physical origin of the Blazhko effect (BL), a phenomenon of a single or multiple periodic modulation(s) of the light curve, is under debate. Efficiently identifying and characterizing the BL is essential in understanding its origins and accounting for its effect on numerous applications of RRabs...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Universe |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-1997/11/1/13 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587333967282176 |
|---|---|
| author | Nan Jiang Tianrui Sun Siyuan Pan Lingzhi Wang Xue Li Bin Sheng Xiaofeng Wang |
| author_facet | Nan Jiang Tianrui Sun Siyuan Pan Lingzhi Wang Xue Li Bin Sheng Xiaofeng Wang |
| author_sort | Nan Jiang |
| collection | DOAJ |
| description | The physical origin of the Blazhko effect (BL), a phenomenon of a single or multiple periodic modulation(s) of the light curve, is under debate. Efficiently identifying and characterizing the BL is essential in understanding its origins and accounting for its effect on numerous applications of RRabs in the era of large time-domain surveys. In this study, we make use of Resnet 34, a well-known convolutional neural network (CNN) architecture, to identify RRab stars with BL from phased light curves collected from OGLE. Using reliably classified RRabs from frequency analysis to train, validate, and test our model, we show that our CNN method reaches accuracies up to 94%. We then applied our CNN method to some additional RRabs located in the Magellanic Cloud (MC) and the Galactic Bulge (GB), leading to the discovery of 113 and 2496 BL candidates, respectively. The identification accuracy for the MC Sample is estimated to be 91% after cross-matching the CNN classification results with those from frequency analysis. Similarly, the light-curve parameters of these classified BL/non-BL candidates by our CNN method from the GB region resemble those observed in the literature, confirming the reliability of our CNN classifications. Our CNN method is subject to issues related to light-curve quality and sampling, but its overall reliance on light-curve quality is comparable to that of frequency analysis. Furthermore, we find that BL modulation could be primarily characterized by variations in light-curve structure. |
| format | Article |
| id | doaj-art-08e88a03a52643bd99e3d2351f1fe828 |
| institution | Kabale University |
| issn | 2218-1997 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Universe |
| spelling | doaj-art-08e88a03a52643bd99e3d2351f1fe8282025-01-24T13:51:29ZengMDPI AGUniverse2218-19972025-01-011111310.3390/universe11010013More Efficient and Reliable: Identifying RRab Stars with Blazhko Effect by Deep Convolutional Neural NetworkNan Jiang0Tianrui Sun1Siyuan Pan2Lingzhi Wang3Xue Li4Bin Sheng5Xiaofeng Wang6David A. Dunlap Department of Astronomy and Astrophysics, University of Toronto, 50 St. George Street, Toronto, ON M5S 3H4, Canada Purple Mountain Observatory, CAS, No. 10 Yuanhua Road, Qixia District, Nanjing 210023, ChinaDepartment of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaChinese Academy of Sciences, South America Center for Astronomy (CASSACA), National Astronomical Observatories, CAS, Beijing 100101, ChinaTsinghua Center for Astrophysics, Physics Department, Tsinghua University, Beijing 100084, ChinaDepartment of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaTsinghua Center for Astrophysics, Physics Department, Tsinghua University, Beijing 100084, ChinaThe physical origin of the Blazhko effect (BL), a phenomenon of a single or multiple periodic modulation(s) of the light curve, is under debate. Efficiently identifying and characterizing the BL is essential in understanding its origins and accounting for its effect on numerous applications of RRabs in the era of large time-domain surveys. In this study, we make use of Resnet 34, a well-known convolutional neural network (CNN) architecture, to identify RRab stars with BL from phased light curves collected from OGLE. Using reliably classified RRabs from frequency analysis to train, validate, and test our model, we show that our CNN method reaches accuracies up to 94%. We then applied our CNN method to some additional RRabs located in the Magellanic Cloud (MC) and the Galactic Bulge (GB), leading to the discovery of 113 and 2496 BL candidates, respectively. The identification accuracy for the MC Sample is estimated to be 91% after cross-matching the CNN classification results with those from frequency analysis. Similarly, the light-curve parameters of these classified BL/non-BL candidates by our CNN method from the GB region resemble those observed in the literature, confirming the reliability of our CNN classifications. Our CNN method is subject to issues related to light-curve quality and sampling, but its overall reliance on light-curve quality is comparable to that of frequency analysis. Furthermore, we find that BL modulation could be primarily characterized by variations in light-curve structure.https://www.mdpi.com/2218-1997/11/1/13stars: variablesRR Lyrae methodsdata analysis techniquesphotometric |
| spellingShingle | Nan Jiang Tianrui Sun Siyuan Pan Lingzhi Wang Xue Li Bin Sheng Xiaofeng Wang More Efficient and Reliable: Identifying RRab Stars with Blazhko Effect by Deep Convolutional Neural Network Universe stars: variables RR Lyrae methods data analysis techniques photometric |
| title | More Efficient and Reliable: Identifying RRab Stars with Blazhko Effect by Deep Convolutional Neural Network |
| title_full | More Efficient and Reliable: Identifying RRab Stars with Blazhko Effect by Deep Convolutional Neural Network |
| title_fullStr | More Efficient and Reliable: Identifying RRab Stars with Blazhko Effect by Deep Convolutional Neural Network |
| title_full_unstemmed | More Efficient and Reliable: Identifying RRab Stars with Blazhko Effect by Deep Convolutional Neural Network |
| title_short | More Efficient and Reliable: Identifying RRab Stars with Blazhko Effect by Deep Convolutional Neural Network |
| title_sort | more efficient and reliable identifying rrab stars with blazhko effect by deep convolutional neural network |
| topic | stars: variables RR Lyrae methods data analysis techniques photometric |
| url | https://www.mdpi.com/2218-1997/11/1/13 |
| work_keys_str_mv | AT nanjiang moreefficientandreliableidentifyingrrabstarswithblazhkoeffectbydeepconvolutionalneuralnetwork AT tianruisun moreefficientandreliableidentifyingrrabstarswithblazhkoeffectbydeepconvolutionalneuralnetwork AT siyuanpan moreefficientandreliableidentifyingrrabstarswithblazhkoeffectbydeepconvolutionalneuralnetwork AT lingzhiwang moreefficientandreliableidentifyingrrabstarswithblazhkoeffectbydeepconvolutionalneuralnetwork AT xueli moreefficientandreliableidentifyingrrabstarswithblazhkoeffectbydeepconvolutionalneuralnetwork AT binsheng moreefficientandreliableidentifyingrrabstarswithblazhkoeffectbydeepconvolutionalneuralnetwork AT xiaofengwang moreefficientandreliableidentifyingrrabstarswithblazhkoeffectbydeepconvolutionalneuralnetwork |