1 code implementation • 21 Mar 2024 • Rithwik Gupta, Daniel Muthukrishna, Michelle Lochner
In this work, we introduce an alternative approach to detecting anomalies: using the penultimate layer of a neural network classifier as the latent space for anomaly detection.
no code implementations • 15 Dec 2021 • Daniel Muthukrishna, Kaisey S. Mandel, Michelle Lochner, Sara Webb, Gautham Narayan
Astronomical transients are stellar objects that become temporarily brighter on various timescales and have led to some of the most significant discoveries in cosmology and astronomy.
no code implementations • 29 Oct 2021 • Daniel Muthukrishna, Kaisey S. Mandel, Michelle Lochner, Sara Webb, Gautham Narayan
We demonstrate our methods' ability to provide anomaly scores as a function of time on light curves from the Zwicky Transient Facility.
1 code implementation • 25 Oct 2021 • Mike Walmsley, Anna M. M. Scaife, Chris Lintott, Michelle Lochner, Verlon Etsebeth, Tobias Géron, Hugh Dickinson, Lucy Fortson, Sandor Kruk, Karen L. Masters, Kameswara Bharadwaj Mantha, Brooke D. Simmons
Models fine-tuned from our representation are better able to identify ring galaxies than models fine-tuned from terrestrial images (ImageNet) or trained from scratch.
1 code implementation • 21 Oct 2020 • Michelle Lochner, Bruce A. Bassett
Here we introduce Astronomaly: a general anomaly detection framework with a novel active learning approach designed to provide personalised recommendations.
Instrumentation and Methods for Astrophysics Astrophysics of Galaxies
1 code implementation • 11 Aug 2020 • Sara Webb, Michelle Lochner, Daniel Muthukrishna, Jeff Cooke, Chris Flynn, Ashish Mahabal, Simon Goode, Igor Andreoni, Tyler Pritchard, Timothy M. C. Abbott
We present an unsupervised method for transient discovery using a clustering technique and the Astronomaly package.
Instrumentation and Methods for Astrophysics
no code implementations • 26 Feb 2019 • Michelle Ntampaka, Camille Avestruz, Steven Boada, Joao Caldeira, Jessi Cisewski-Kehe, Rosanne Di Stefano, Cora Dvorkin, August E. Evrard, Arya Farahi, Doug Finkbeiner, Shy Genel, Alyssa Goodman, Andy Goulding, Shirley Ho, Arthur Kosowsky, Paul La Plante, Francois Lanusse, Michelle Lochner, Rachel Mandelbaum, Daisuke Nagai, Jeffrey A. Newman, Brian Nord, J. E. G. Peek, Austin Peel, Barnabas Poczos, Markus Michael Rau, Aneta Siemiginowska, Dougal J. Sutherland, Hy Trac, Benjamin Wandelt
In recent years, machine learning (ML) methods have remarkably improved how cosmologists can interpret data.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics
no code implementations • 22 Feb 2019 • Ethan Roberts, Bruce A. Bassett, Michelle Lochner
Using simulated data with Gaussian noise, BADAC is shown to be superior to standard algorithms in both classification and anomaly detection performance in the presence of uncertainties, though with significantly increased computational cost.
3 code implementations • 28 Sep 2018 • The PLAsTiCC team, Tarek Allam Jr., Anita Bahmanyar, Rahul Biswas, Mi Dai, Lluís Galbany, Renée Hložek, Emille E. O. Ishida, Saurabh W. Jha, David O. Jones, Richard Kessler, Michelle Lochner, Ashish A. Mahabal, Alex I. Malz, Kaisey S. Mandel, Juan Rafael Martínez-Galarza, Jason D. McEwen, Daniel Muthukrishna, Gautham Narayan, Hiranya Peiris, Christina M. Peters, Kara Ponder, Christian N. Setzer, The LSST Dark Energy Science Collaboration, The LSST Transients, Variable Stars Science Collaboration
The Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC) is an open data challenge to classify simulated astronomical time-series data in preparation for observations from the Large Synoptic Survey Telescope (LSST), which will achieve first light in 2019 and commence its 10-year main survey in 2022.
Instrumentation and Methods for Astrophysics Solar and Stellar Astrophysics
1 code implementation • 7 Jul 2018 • A. Vafaei Sadr, Etienne. E. Vos, Bruce A. Bassett, Zafiirah Hosenie, N. Oozeer, Michelle Lochner
For uniformly-weighted images it achieves a Purity x Completeness (PC) score at SNR = 3 of 0. 73, compared to 0. 31 for the best PyBDSF model.
1 code implementation • 12 Feb 2018 • Luisa Lucie-Smith, Hiranya V. Peiris, Andrew Pontzen, Michelle Lochner
We train a machine learning algorithm to learn cosmological structure formation from N-body simulations.
Cosmology and Nongalactic Astrophysics Instrumentation and Methods for Astrophysics
1 code implementation • 14 Aug 2017 • LSST Science Collaboration, Phil Marshall, Timo Anguita, Federica B. Bianco, Eric C. Bellm, Niel Brandt, Will Clarkson, Andy Connolly, Eric Gawiser, Zeljko Ivezic, Lynne Jones, Michelle Lochner, Michael B. Lund, Ashish Mahabal, David Nidever, Knut Olsen, Stephen Ridgway, Jason Rhodes, Ohad Shemmer, David Trilling, Kathy Vivas, Lucianne Walkowicz, Beth Willman, Peter Yoachim, Scott Anderson, Pierre Antilogus, Ruth Angus, Iair Arcavi, Humna Awan, Rahul Biswas, Keaton J. Bell, David Bennett, Chris Britt, Derek Buzasi, Dana I. Casetti-Dinescu, Laura Chomiuk, Chuck Claver, Kem Cook, James Davenport, Victor Debattista, Seth Digel, Zoheyr Doctor, R. E. Firth, Ryan Foley, Wen-fai Fong, Lluis Galbany, Mark Giampapa, John E. Gizis, Melissa L. Graham, Carl Grillmair, Phillipe Gris, Zoltan Haiman, Patrick Hartigan, Suzanne Hawley, Renee Hlozek, Saurabh W. Jha, C. Johns-Krull, Shashi Kanbur, Vassiliki Kalogera, Vinay Kashyap, Vishal Kasliwal, Richard Kessler, Alex Kim, Peter Kurczynski, Ofer Lahav, Michael C. Liu, Alex Malz, Raffaella Margutti, Tom Matheson, Jason D. McEwen, Peregrine McGehee, Soren Meibom, Josh Meyers, Dave Monet, Eric Neilsen, Jeffrey Newman, Matt O'Dowd, Hiranya V. Peiris, Matthew T. Penny, Christina Peters, Radoslaw Poleski, Kara Ponder, Gordon Richards, Jeonghee Rho, David Rubin, Samuel Schmidt, Robert L. Schuhmann, Avi Shporer, Colin Slater, Nathan Smith, Marcelles Soares-Santos, Keivan Stassun, Jay Strader, Michael Strauss, Rachel Street, Christopher Stubbs, Mark Sullivan, Paula Szkody, Virginia Trimble, Tony Tyson, Miguel de Val-Borro, Stefano Valenti, Robert Wagoner, W. Michael Wood-Vasey, Bevin Ashley Zauderer
The Large Synoptic Survey Telescope is designed to provide an unprecedented optical imaging dataset that will support investigations of our Solar System, Galaxy and Universe, across half the sky and over ten years of repeated observation.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Earth and Planetary Astrophysics Astrophysics of Galaxies Solar and Stellar Astrophysics