Automated Blazar Light Curves Using Machine Learning

Technical Report · Thu Jul 27 04:00:00 EDT 2017

DOI:https://doi.org/10.2172/1373503· OSTI ID:1373503

Johnson, Spencer James ^[1]

---

1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Every night in a remote clearing called Fenton Hill high in the Jemez Mountains of central New Mexico, a bank of robotically controlled telescopes tilt their lenses to the sky for another round of observation through digital imaging. Los Alamos National Laboratory’s Thinking Telescopes project is watching for celestial transients including high-power cosmic flashes called, and like all science, it can be messy work. To keep the project clicking along, Los Alamos scientists routinely install equipment upgrades, maintain the site, and refine the sophisticated machinelearning computer programs that process those images and extract useful data from them. Each week the system amasses 100,000 digital images of the heavens, some of which are compromised by clouds, wind gusts, focus problems, and so on. For a graduate student at the Lab taking a year’s break between master’s and Ph.D. studies, working with state-of-the-art autonomous telescopes that can make fundamental discoveries feels light years beyond the classroom.

• Research Organization: Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE; NASA
• DOE Contract Number: AC52-06NA25396
• OSTI ID: 1373503
• Report Number(s): LA-UR--17-25456
• Country of Publication: United States
• Language: English

Related Subjects

79 ASTRONOMY AND ASTROPHYSICS
97 MATHEMATICS AND COMPUTING