More Like this

1. Deblending and Classifying Astronomical Sources with Mask R-CNN Deep Learning

   Colin J Burke, Patrick D (October 2019, Monthly notices of the Royal Astronomical Society)

   e apply a new deep learning technique to detect, classify, and deblend sources in multi-band astronomical images. We train and evaluate the performance of an artificial neural network built on the Mask R-CNN image processing framework, a general code for efficient object detection, classification, and instance segmentation. After evaluating the performance of our network against simulated ground truth images for star and galaxy classes, we find a precision of 92% at 80% recall for stars and a precision of 98% at 80% recall for galaxies in a typical field with ∼30 galaxies/arcmin2. We investigate the deblending capability of our code, and find that clean deblends are handled robustly during object masking, even for significantly blended sources. This technique, or extensions using similar network architectures, may be applied to current and future deep imaging surveys such as LSST and WFIRST. Our code, Astro R-CNN, is publicly available at https://github.com/burke86/astro_rcnn 

   more » « less
2. Detection, instance segmentation, and classification for astronomical surveys with deep learning ( deepdisc ): detectron2 implementation and demonstration with Hyper Suprime-Cam data

   https://doi.org/10.1093/mnras/stad2785  

   Merz, Grant; Liu, Yichen; Burke, Colin_J; Aleo, Patrick_D; Liu, Xin; Carrasco Kind, Matias; Kindratenko, Volodymyr; Liu, Yufeng (September 2023, Monthly Notices of the Royal Astronomical Society)

   ABSTRACT The next generation of wide-field deep astronomical surveys will deliver unprecedented amounts of images through the 2020s and beyond. As both the sensitivity and depth of observations increase, more blended sources will be detected. This reality can lead to measurement biases that contaminate key astronomical inferences. We implement new deep learning models available through Facebook AI Research’s detectron2 repository to perform the simultaneous tasks of object identification, deblending, and classification on large multiband co-adds from the Hyper Suprime-Cam (HSC). We use existing detection/deblending codes and classification methods to train a suite of deep neural networks, including state-of-the-art transformers. Once trained, we find that transformers outperform traditional convolutional neural networks and are more robust to different contrast scalings. Transformers are able to detect and deblend objects closely matching the ground truth, achieving a median bounding box Intersection over Union of 0.99. Using high-quality class labels from the Hubble Space Telescope, we find that when classifying objects as either stars or galaxies, the best-performing networks can classify galaxies with near 100 per cent completeness and purity across the whole test sample and classify stars above 60 per cent completeness and 80 per cent purity out to HSC i-band magnitudes of 25 mag. This framework can be extended to other upcoming deep surveys such as the Legacy Survey of Space and Time and those with the Roman Space Telescope to enable fast source detection and measurement. Our code, deepdisc, is publicly available at https://github.com/grantmerz/deepdisc. 

   more » « less
3. A Red-noise Eigenbasis for the Reconstruction of Blobby Images

   https://doi.org/10.3847/1538-4357/ac502a  

   Hallur, Pravita; Medeiros, Lia; Lauer, Tod R. (March 2022, The Astrophysical Journal)

   Abstract We demonstrate the use of an eigenbasis that is derived from principal component analysis (PCA) applied on an ensemble of random-noise images that have a “red” power spectrum; i.e., a spectrum that decreases smoothly from large to small spatial scales. The pattern of the resulting eigenbasis allows for the reconstruction of images with a broad range of image morphologies. In particular, we show that this general eigenbasis can be used to efficiently reconstruct images that resemble possible astronomical sources for interferometric observations, even though the images in the original ensemble used to generate the PCA basis are significantly different from the astronomical images. We further show that the efficiency and fidelity of the image reconstructions depends only weakly on the particular parameters of the red-noise power spectrum used to generate the ensemble of images. 

   more » « less
4. The DECam Local Volume Exploration Survey Data Release 2

   https://doi.org/10.3847/1538-4365/ac78eb  

   Drlica-Wagner, A.; Ferguson, P. S.; Adamów, M.; Aguena, M.; Allam, S.; Andrade-Oliveira, F.; Bacon, D.; Bechtol, K.; Bell, E. F.; Bertin, E.; et al (August 2022, The Astrophysical Journal Supplement Series)

   Abstract We present the second public data release (DR2) from the DECam Local Volume Exploration survey (DELVE). DELVE DR2 combines new DECam observations with archival DECam data from the Dark Energy Survey, the DECam Legacy Survey, and other DECam community programs. DELVE DR2 consists of ∼160,000 exposures that cover >21,000 deg 2 of the high-Galactic-latitude (∣ b ∣ > 10°) sky in four broadband optical/near-infrared filters ( g , r , i , z ). DELVE DR2 provides point-source and automatic aperture photometry for ∼2.5 billion astronomical sources with a median 5 σ point-source depth of g = 24.3, r = 23.9, i = 23.5, and z = 22.8 mag. A region of ∼17,000 deg 2 has been imaged in all four filters, providing four-band photometric measurements for ∼618 million astronomical sources. DELVE DR2 covers more than 4 times the area of the previous DELVE data release and contains roughly 5 times as many astronomical objects. DELVE DR2 is publicly available via the NOIRLab Astro Data Lab science platform. 

   more » « less
5. Finding quadruply imaged quasars with machine learning – I. Methods

   https://doi.org/10.1093/mnras/stac925  

   Akhazhanov, A; More, A; Amini, A; Hazlett, C; Treu, T; Birrer, S; Shajib, A; Liao, K; Lemon, C; Agnello, A; et al (May 2022, Monthly Notices of the Royal Astronomical Society)

   ABSTRACT Strongly lensed quadruply imaged quasars (quads) are extraordinary objects. They are very rare in the sky and yet they provide unique information about a wide range of topics, including the expansion history and the composition of the Universe, the distribution of stars and dark matter in galaxies, the host galaxies of quasars, and the stellar initial mass function. Finding them in astronomical images is a classic ‘needle in a haystack’ problem, as they are outnumbered by other (contaminant) sources by many orders of magnitude. To solve this problem, we develop state-of-the-art deep learning methods and train them on realistic simulated quads based on real images of galaxies taken from the Dark Energy Survey, with realistic source and deflector models, including the chromatic effects of microlensing. The performance of the best methods on a mixture of simulated and real objects is excellent, yielding area under the receiver operating curve in the range of 0.86–0.89. Recall is close to 100 per cent down to total magnitude i ∼ 21 indicating high completeness, while precision declines from 85 per cent to 70 per cent in the range i ∼ 17–21. The methods are extremely fast: training on 2 million samples takes 20 h on a GPU machine, and 108 multiband cut-outs can be evaluated per GPU-hour. The speed and performance of the method pave the way to apply it to large samples of astronomical sources, bypassing the need for photometric pre-selection that is likely to be a major cause of incompleteness in current samples of known quads. 

   more » « less