Machine learning for transient recognition in difference imaging with minimum sampling effort
| العنوان: | Machine learning for transient recognition in difference imaging with minimum sampling effort |
|---|---|
| المؤلفون: | L. K. Nuttall, U. Burhanudin, Danny Steeghs, Klaas Wiersema, Paul Chote, Christopher J. Duffy, Andrew J. Levan, Enric Palle, P. T. O'Brien, Y. L. Mong, Saran Poshyachinda, S. Aukkaravittayapun, James McCormac, E. Rol, Seppo Mattila, E. J. Daw, Puji Irawati, James Mullaney, J. D. Lyman, R. Eyles-Ferris, D. Mata Sánchez, Kendall Ackley, Rene P. Breton, Don Pollacco, Martin J. Dyer, R. L. C. Starling, A. Obradovic, A. Chrimes, T. Heikkilä, Supachai Awiphan, Elizabeth R. Stanway, Krzysztof Ulaczyk, S. Tooke, T. Killestein, Eric Thrane, T. R. Marsh, B. P. Gompertz, Rubina Kotak, Utane Sawangwit, L. Makrygianni, S. P. Littlefair, David Mkrtichian, V. S. Dhillon, Mark Kennedy, Duncan K. Galloway, R. Cutter, Justyn R. Maund, G. Ramsay |
| المصدر: | Monthly Notices of the Royal Astronomical Society Mong, Y-L, Ackley, K, Galloway, D, Killestein, T, Lyman, J, Steeghs, D, Dhillon, V, O'Brien, P, Ramsay, G, Poshyachinda, S, Kotak, R, Nuttall, L, Pall'e, E, Pollacco, D, Thrane, E, Dyer, M, Ulaczyk, K, Cutter, R, McCormac, J, Chote, P, Levan, A, Marsh, T, Stanway, E, Gompertz, B, Wiersema, K, Chrimes, A, Obradovic, A, Mullaney, J, Daw, E, Littlefair, S, Maund, J, Makrygianni, L, Burhanudin, U, Starling, R, Eyles, R, Tooke, S, Duffy, C, Aukkaravittayapun, S, Sawangwit, U, Awiphan, S, Mkrtichian, D, Irawati, P, Mattila, S, Heikkil"a, T, Breton, R, Kennedy, M, Mata-Sanchez, D & Rol, E 2020, ' Machine learning for transient recognition in difference imaging with minimum sampling effort ', Monthly Notices of the Royal Astronomical Society, vol. 499, no. 4, pp. 6009-6017 . https://doi.org/10.1093/mnras/staa3096 arXiv |
| سنة النشر: | 2020 |
| مصطلحات موضوعية: | Goto, statistical [methods], FOS: Physical sciences, Machine learning, computer.software_genre, 01 natural sciences, Constant false alarm rate, Methods statistical, 0103 physical sciences, data analysis [methods], 010306 general physics, Instrumentation and Methods for Astrophysics (astro-ph.IM), 010303 astronomy & astrophysics, Physics, Training set, Pixel, image processing [techniques], business.industry, Astronomy and Astrophysics, Space and Planetary Science, Artificial intelligence, business, Astrophysics - Instrumentation and Methods for Astrophysics, computer, Classifier (UML), astro-ph.IM |
| الوصف: | The amount of observational data produced by time-domain astronomy is exponentially in-creasing. Human inspection alone is not an effective way to identify genuine transients fromthe data. An automatic real-bogus classifier is needed and machine learning techniques are commonly used to achieve this goal. Building a training set with a sufficiently large number of verified transients is challenging, due to the requirement of human verification. We presentan approach for creating a training set by using all detections in the science images to be thesample of real detections and all detections in the difference images, which are generated by the process of difference imaging to detect transients, to be the samples of bogus detections. This strategy effectively minimizes the labour involved in the data labelling for supervised machine learning methods. We demonstrate the utility of the training set by using it to train several classifiers utilizing as the feature representation the normalized pixel values in 21-by-21pixel stamps centered at the detection position, observed with the Gravitational-wave Optical Transient Observer (GOTO) prototype. The real-bogus classifier trained with this strategy can provide up to 95% prediction accuracy on the real detections at a false alarm rate of 1%. 9 pages, 8 figures |
| وصف الملف: | application/pdf |
| تدمد: | 0035-8711 |
| DOI: | 10.1093/mnras/staa3096 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::32e485f5c72e9682f2ed37dc3b1eecdf |
| حقوق: | OPEN |
| رقم الأكسشن: | edsair.doi.dedup.....32e485f5c72e9682f2ed37dc3b1eecdf |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 00358711 |
|---|---|
| DOI: | 10.1093/mnras/staa3096 |