The Modern Astrophysics Stack: Automated Action and Insight
summary
Describes an automated end-to-end pipeline: robotic telescopes that slew to GRBs within a minute, a survey ingesting 1.5 million nightly candidates that reduces to ~1,000 then ~10 real transients, and machine-learning classifiers that cut false positives and produce calibrated probabilities. Claims include LSST-scale rates (20 TB/night, ~1 million SNe/yr) and a concrete success — discovery of a Type Ia ~11 hours after explosion whose early non-detections rule out many progenitor models. Presents transfer learning, active learning, and a working real‑time classification stack.
AI-written summary · about
chapters (4)
- 0:00Start
- 23:00Astronomy OF THE ROBOTIC TELESCOPES
- 24:08Automating Discovery
- 36:19Automating Classification
related talks
33mPython VS Space Junk
45mRadio Astronomy for Programmers
35mAstrophysics to data Science: how the Milky Way is like my company.
11mBig Data Moonshots and Ground Control
43mProcessing Data From The James Webb Space Telescope
28mAstronomy with Python, for non-astronomers
35mStreaming the Universe: When the Sky Became Big Data
39mLightning Talks