Application of Convolutional Neural Networks to time domain astrophysics. 2D image analysis of OGLE light curves
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909383896596480 |
|---|---|
| author | Monsalves, N. Arancibia, M. Jaque Bayo, A. Sánchez-Sáez, P. Angeloni, R. Damke, G Van de Perre, J. Segura |
| author_facet | Monsalves, N. Arancibia, M. Jaque Bayo, A. Sánchez-Sáez, P. Angeloni, R. Damke, G Van de Perre, J. Segura |
| contents | In recent years the amount of publicly available astronomical data has increased exponentially, with a remarkable example being large scale multiepoch photometric surveys. This wealth of data poses challenges to the classical methodologies commonly employed in the study of variable objects. As a response, deep learning techniques are increasingly being explored to effectively classify, analyze, and interpret these large datasets. In this paper we use two-dimensional histograms to represent Optical Gravitational Lensing Experiment (OGLE) phasefolded light curves as images. We use a Convolutional Neural Network (CNN) to classify variable objects within eight different categories (from now on labels): Classical Cepheid (CEP), RR Lyrae (RR), Long Period Variable (LPV), Miras (M), Ellipsoidal Binary (ELL), Delta Scuti (DST), Eclipsing Binary (E), and spurious class with Incorrect Periods (Rndm). We set up different training sets to train the same CNN architecture in order to characterize the impact of the training. The training sets were built from the same source of labels but different filters and balancing techniques were applied. Namely: Undersampling (U), Data Augmentation (DA), and Batch Balancing (BB). The best performance was achieved with the BB approach and a training sample size of $\sim$370000 stars. Regarding computational performance, the image representation production rate is of $\sim$76 images per core per second, and the time to predict is $\sim$ 60$\, μ\text{s}$ per star. The accuracy of the classification improves from $\sim$ 92%, when based only on the CNN, to $\sim$ 98% when the results of the CNN are combined with the period and amplitude features in a two step approach. This methodology achieves comparable results with previous studies but with two main advantages: the identification of miscalculated periods and the improvement in computational time cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11960 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Application of Convolutional Neural Networks to time domain astrophysics. 2D image analysis of OGLE light curves Monsalves, N. Arancibia, M. Jaque Bayo, A. Sánchez-Sáez, P. Angeloni, R. Damke, G Van de Perre, J. Segura Instrumentation and Methods for Astrophysics Solar and Stellar Astrophysics In recent years the amount of publicly available astronomical data has increased exponentially, with a remarkable example being large scale multiepoch photometric surveys. This wealth of data poses challenges to the classical methodologies commonly employed in the study of variable objects. As a response, deep learning techniques are increasingly being explored to effectively classify, analyze, and interpret these large datasets. In this paper we use two-dimensional histograms to represent Optical Gravitational Lensing Experiment (OGLE) phasefolded light curves as images. We use a Convolutional Neural Network (CNN) to classify variable objects within eight different categories (from now on labels): Classical Cepheid (CEP), RR Lyrae (RR), Long Period Variable (LPV), Miras (M), Ellipsoidal Binary (ELL), Delta Scuti (DST), Eclipsing Binary (E), and spurious class with Incorrect Periods (Rndm). We set up different training sets to train the same CNN architecture in order to characterize the impact of the training. The training sets were built from the same source of labels but different filters and balancing techniques were applied. Namely: Undersampling (U), Data Augmentation (DA), and Batch Balancing (BB). The best performance was achieved with the BB approach and a training sample size of $\sim$370000 stars. Regarding computational performance, the image representation production rate is of $\sim$76 images per core per second, and the time to predict is $\sim$ 60$\, μ\text{s}$ per star. The accuracy of the classification improves from $\sim$ 92%, when based only on the CNN, to $\sim$ 98% when the results of the CNN are combined with the period and amplitude features in a two step approach. This methodology achieves comparable results with previous studies but with two main advantages: the identification of miscalculated periods and the improvement in computational time cost. |
| title | Application of Convolutional Neural Networks to time domain astrophysics. 2D image analysis of OGLE light curves |
| topic | Instrumentation and Methods for Astrophysics Solar and Stellar Astrophysics |
| url | https://arxiv.org/abs/2408.11960 |