Laying the Foundation for Complete Automation in Particle Image Inference

by Francois Drielsma (SLAC)

Thursday 22 Feb 2024, 11:00 → 12:00 America/Los_Angeles

53/2-2002 - Berryessa (SLAC)

 

Particle imaging detectors have had a ubiquitous role in particle physics for over a century. The unrivaled level of detail they deliver has led to many discoveries and continues to make them an attractive choice in modern experiments. The liquid argon time projection chamber (LArTPC) technology – a dense, scalable realization of this detection paradigm – is the cornerstone of the US-based accelerator neutrino program. While the human brain can reliably recognize patterns in particle interaction images, automating this reconstruction process has been an ongoing challenge which could jeopardize the success of LArTPC experiments. Recent leaps in computer vision, made possible by machine learning (ML), have led to a remedy. We introduce an ML-based data reconstruction chain for particle imaging detectors: a multi-task network cascade which combines voxel-level feature extraction using Sparse Convolutional Neural Networks and particle superstructure formation using Graph Neural Networks. It provides a detailed description of an image and is currently used for state-of-the-art physics inference in three LArTPC experiments. Building on this success, we propose to explore the potential of leveraging self-supervised learning – the core concept of cutting-edge large language models – to learn the fundamental structure of detector data directly from a large corpus of raw, unlabeled data waveforms, the natural language of LArTPCs and most other detectors. This novel approach could address current shortcomings in signal processing and bring the impact of data/simulation disagreement under control. In addition, a model which successfully captures these data patterns could constitute a foundation model, i.e. a singular algorithm which forms the basis to perform all reconstruction tasks.

 

 

Slides     Zoom recording. (The presentation begins at  00:01:20 )

 

Zoom information:

Join from PC, Mac, Linux, iOS or Android: https://stanford.zoom.us/j/95737044758?pwd=eitXVzhUZmIybHBrdy9QR1J6TW9oUT09

    Password: 889466

 

Or iPhone one-tap (US Toll): +18333021536,,95737044758# or +16507249799,,95737044758#

 

Or Telephone:

    Dial: +1 650 724 9799 (US, Canada, Caribbean Toll) or +1 833 302 1536 (US, Canada, Caribbean Toll Free)

         

    Meeting ID: 957 3704 4758

    Password: 889466

    International numbers available: https://stanford.zoom.us/u/acWEw3Cvkr

 

    Meeting ID: 957 3704 4758

    Password: 889466

    SIP: 95737044758@zoomcrc.com

    Password: 889466

 

 

 

Drielsma - Panofsky Seminar.pdf