Technical Event
Tutorial and Closing Remarks
15 October 2021 • 10:00 AM - 11:45 AM EDT icon_live_event.svg
Recording will be available soon
Available to Registered Attendees of the SPIE Laser Damage Digital Forum

Sign in now or Register to access
All Times listed in Eastern Daylight Time

Session moderator: Chris Stolz, Lawrence Livermore National Laboratory (United States)

Tutorial on Machine Learning in Design of Optical Components
Laura Mascio Kegelmeyer, Lawrence Livermore National Laboratory (United States)

A practical guide to machine learning for managing Laser Damage

This event occurred in the past. Click here to view now.

This tutorial provides an overview of machine learning methods and the practical steps needed for implementation. We will use examples from NIF to demonstrate steps from data preparation to the pros and cons of different machine learning methods.

Laura Mascio Kegelmeyer has been engaged in the science and engineering of image analysis at Lawrence Livermore National Laboratory for over thirty years. Her first domain was biomedical sciences; developing methods for automated microscopy, microarray analysis, and x-ray inspections including breast cancer detection. In 2000, she founded Optics Inspection Analysis for the NIF (National Ignition Facility), specializing in images from cameras throughout the 192 beamlines of the high energy laser facility. Since then, she’s led teams to develop and operate over 20 different inspection systems, such as analyzing images from: off-beamline microscopy labs where optics are repaired for re-use, laser wavefront sensor data, and the shell of capsules used in target fabrication. These require research, innovative custom analysis and practical data science engineering to support on-going production operations.

Closing Remarks provided by Conference Chairs