BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//INPA - ECPv6.8.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:INPA
X-ORIGINAL-URL:https://inpa.lbl.gov
X-WR-CALDESC:Events for INPA
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20240310T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20241103T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20240201T120000
DTEND;TZID=America/Los_Angeles:20240201T130000
DTSTAMP:20260426T091939
CREATED:20240116T185743Z
LAST-MODIFIED:20240129T203636Z
UID:1655-1706788800-1706792400@inpa.lbl.gov
SUMMARY:[Special] Speaker: Mark Anderson(Queen's University) Title: Advancing nuclear and particle physics with deep learning: from event reconstruction to signal denoising
DESCRIPTION:SPECIAL INPA SEMINAR \nDate:  Thursday\, February 1\, 2024 \nTime: 12:00 PM – 1:00 PM \nLocation: INPA Conference Room–5026 [Hybrid and In-Person] \nSpeaker: Mark Anderson (Queen’s University) \nTitle: Advancing nuclear and particle physics with deep learning: from event reconstruction to signal denoising \nAbstract: In this talk\, I will present my research on advancing nuclear and particle physics using deep learning. The first portion of the presentation will focus on the SNO+ experiment\, a multi-purpose neutrino experiment with the primary goal of searching for neutrinoless double-beta decay. In particular\, my work involves developing deep learning-based techniques for event reconstruction of particle interactions in the detector. Currently\, SNO+ uses a chain of algorithms involving maximum likelihood estimation. I will demonstrate that my independent\, deep learning approach can be used to improve the reconstruction accuracy\, while also offering substantial gains in speed. This has implications on volume fiducialization and background rejection.\nIn the second part of my talk\, I will present studies on a deep convolutional autoencoder designed to remove electronic noise from a p-type point contact high purity germanium detector. With their intrinsic purity and excellent energy resolutions\, these detectors are suitable for a variety of rare event searches such as neutrinoless double-beta decay\, dark matter candidates\, and other exotic physics. However\, noise from the readout electronics can make identifying events of interest more challenging. I will highlight several studies that show that detector performance can be improved when signals are denoised with the autoencoder\, leading to better physics outcomes.\nWhile both of these projects are applied to data from specific detector technologies\, the methods I have developed are broadly applicable. The groups I work with have begun exploring new applications of my research with promising results. At the end of the talk\, I will discuss some specific extensions and provide an outlook for the future. \nJoin Zoom Meeting\nhttps://lbnl.zoom.us/j/95016696011?pwd=Tk1XOW1Xd3RYRnlsc2tEYmRWZlVVZz09 \nMeeting ID: 950 1669 6011 \nPasscode: 247722
URL:https://inpa.lbl.gov/event/speaker-mark-anderson-queens-university-title-tba/
END:VEVENT
END:VCALENDAR