Machine Learning Advantages in Canadian Astrophysics

Venn, Kim; Fabbro, S.; Liu, A; Hezaveh, Yashar; Perreault-Levasseur, Laurence; Eadie, Gwendolyn; Ellison, Stephen L. R.; Woo, Jiyoung; Kavelaars, J. J.; Yi, Kyongsu; Hložek, Renée; Bovy, Jo; Teimoorinia, Hossen; Ravanbakhsh, Siamak; Spencer, L. D.

doi:10.5281/zenodo.3755910

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent advances in deep learning have demonstrated the impressive versatility of these advanced methods for a variety of tasks (e.g., Silver et al 2017, Esteva et al 2017, and Hezaveh et al 2017). In the specific field of astrophysics and astronomy, they have also been shown to have broad applicability (see Venn et al 2019, Hložek 2019, Siemiginowska et al 2019 and references therein for a review of recent applications of deep learning in astrophysics and astronomy), in particular for denoising and super-resolution (see, e.g., Ulyanov et al 2020, Baso et al 2019, Wei & Huerta 2020. Machine learning, and in particular deep learning, now offers a new way to remove correlated noise and construct science images.…”

Section: Introductionmentioning

confidence: 99%

Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning

Payeur,

Artigau,

Perreault-Levasseur

et al. 2022

Preprint

View full text Add to dashboard Cite

We present a new procedure rooted in deep learning to construct science images from data cubes collected by astronomical instruments using HxRG detectors in low-flux regimes. It improves on the drawbacks of the conventional algorithms to construct 2D images from multiple readouts by using the readout scheme of the detectors to reduce the impact of correlated readout noise. We train a convolutional recurrent neural network on simulated astrophysical scenes added to laboratory darks to estimate the flux on each pixel of science images. This method achieves a reduction of the noise on constructed science images when compared to standard flux-measurement schemes (correlated double sampling, up-the-ramp sampling), which results in a reduction of the error on the spectrum extracted from these science images. Over simulated data cubes created in a low signal-to-noise ratio regime where this method could have the largest impact, we find that the error on our constructed science images falls faster than a 1/ √ N decay, and that the spectrum extracted from the images has, averaged over a test set of three images, a standard error reduced by a factor of 1.85 in comparison to the standard up-the-ramp pixel sampling scheme. The code used in this project is publicly available on GitHub a)

show abstract

Section: Introductionmentioning

confidence: 99%

Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning

Payeur,

Artigau,

Perreault-Levasseur

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning

Guillaume

Artigau

Perreault-Levasseur

et al. 2022

View full text Add to dashboard Cite

We present a new procedure rooted in deep learning to construct science images from data cubes collected by astronomical instruments using HxRG detectors in low-flux regimes. It improves on the drawbacks of the conventional algorithms to construct 2D images from multiple readouts by using the readout scheme of the detectors to reduce the impact of correlated readout noise. We train a convolutional recurrent neural network on simulated astrophysical scenes added to laboratory darks to estimate the flux on each pixel of science images. This method achieves a reduction of the noise on constructed science images when compared to standard flux-measurement schemes (correlated double sampling, up-the-ramp sampling), which results in a reduction of the error on the spectrum extracted from these science images. Over simulated data cubes created in a low signal-to-noise ratio regime where this method could have the largest impact, we find that the error on our constructed science images falls faster than a 1 / N decay, and that the spectrum extracted from the images has, averaged over a test set of three images, a standard error reduced by a factor of 1.85 in comparison to the standard up-the-ramp pixel sampling scheme. The code used in this project is publicly available on GitHub 7 7 https://github.com/GuillaumePayeur/HxRG-denoiser

show abstract

Application of Deep-learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM Time-tagged Event Data

Zhang 张,

Li 李,

Gui 桂

et al. 2024

ApJS

View full text Add to dashboard Cite

To investigate gamma-ray bursts (GRBs) in depth, it is crucial to develop an effective method for identifying GRBs accurately. Current criteria, e.g., onboard blind search, ground blind search, and target search, are limited by manually set thresholds and perhaps miss GRBs, especially for subthreshold events. We proposed a novel approach that utilizes convolutional neural networks (CNNs) to distinguish GRBs and non-GRBs directly. We structured three CNN models, plain-CNN, ResNet, and ResNet-CBAM, and endeavored to exercise fusing strategy models. Count maps of NaI detectors on board Fermi/Gamma-ray Burst Monitor were employed, as the input samples of data sets and models were implemented to evaluate their performance on different timescale data. The ResNet-CBAM model trained on the 64 ms data set achieves high accuracy overall, which includes residual and attention mechanism modules. The visualization methods of Grad-CAM and t-SNE explicitly displayed that the optimal model focuses on the key features of GRBs precisely. The model was applied to analyze 1 yr data, accurately identifying approximately 98% of GRBs listed in the Fermi burst catalog, eight out of nine subthreshold GRBs, and five GRBs triggered by other satellites, which demonstrated that the deep-learning methods could effectively distinguish GRBs from observational data. Besides, thousands of unknown candidates were retrieved and compared with the bursts of SGR J1935+2154, for instance, which exemplified the potential scientific value of these candidates indeed. Detailed studies on integrating our model into real-time analysis pipelines thus may improve their accuracy of inspection and provide valuable guidance for rapid follow-up observations of multiband telescopes.

show abstract

Machine Learning Advantages in Canadian Astrophysics

Cited by 3 publications

References 4 publications

Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning

Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning

Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning

Application of Deep-learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM Time-tagged Event Data

Contact Info

Product

Resources

About