BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:CD Technical Meeting (VI5): Combined talks: Interactive Tools & Di
 gitals Twins
DTSTART:20261021T090000Z
DTEND:20261021T100000Z
DTSTAMP:20261022T213200Z
UID:indico-event-862@indico.ukaea.uk
DESCRIPTION:Speakers: Rui Costa\, Samuel (Computing) Jackson (UKAEA)\n\nVi
 sualisation and Integration\n1. Interactive Tooling for Tokamak Data Annot
 ation and Exploration\nSamuel Jackson\nEffective interpretation of tokamak
  experimental data requires not only scalable analysis pipelines but also 
 intuitive interfaces that enable physicists\, machine learning practitione
 rs\, and data engineers to rapidly label\, explore\, and contextualise lar
 ge shot catalogues. We present two open-source tools developed at UKAEA th
 at address complementary stages of this workflow\, from structured data an
 notation through to interactive exploratory analysis.\nThe first tool\, 
 “Toktagger”\, is a web-based annotation platform for curating labelled
  datasets from tokamak diagnostics. It provides an intuitive interface for
  browsing shots\, inspecting diagnostic data\, and applying consistent lab
 els through a customisable tagging system. The tool supports interactive m
 ulti-modality labelling of time series traces\, spectrograms\, and camera 
 data. Integrated machine learning model support enables data driven workfl
 ows to automate the annotation cycle\, accelerating the creation of high-q
 uality training datasets for downstream tasks such as disruption precursor
  analysis and regime classification.\nThe second tool\, “NiceShot!” is
  an interactive web-based dashboard for exploring tabular shot metadata ac
 ross entire experimental campaigns. It provides dimensionality reduction p
 rojections of the shot space\, pairwise scatter plots\, sortable data tabl
 es\, and per-shot time-trace visualisation\, all updated live through a fl
 exible filtering system. Additional features include clustering & outlier 
 detection methods\, as well as feature attribution plots to support interp
 retable analysis of data-driven models\, helping physicists understand whi
 ch plasma parameters drive shot-level predictions. The tool connects direc
 tly to different backend data access layers\, making deployment against ex
 isting data infrastructure straightforward.\nTogether\, these tools form a
  practical pipeline connecting broad exploratory analysis\, filtering and 
 quality analysis\, through to supporting the human-in-the-loop annotation 
 workflows leading to high quality datasets. We will demonstrate both tools
  on MAST/MAST-U data and discuss lessons learned\, open challenges\, and o
 pportunities for wider community contribution.\n \n2. Building digital tw
 in experiences of fusion facilities with OpenUSD\n \nRui Costa\n \nMakin
 g fusion energy commercially viable is a complex\, multidisciplinary chall
 enge that depends on teams with very different expertise working through i
 ntegrated\, traceable workflows. In this talk we show how UKAEA is using O
 penUSD (Universal Scene Description) as the foundation for custom digital 
 twin experiences and scalable data pipelines: an open framework for compos
 ing 3D worlds that can bring together engineering geometry\, metadata\, re
 al-time operational data and simulation results in a unified\, extensible 
 environment. Because OpenUSD is an open standard that can support many app
 lications and deployment routes\, it provides flexibility in how these dig
 ital twin workflows are built and used\; in our case\, we use NVIDIA Omniv
 erse for the real-time collaboration\, visualization\, simulation and inte
 roperability features it provides\, as well as our access to OVX hardware.
  Built on OpenUSD\, NVIDIA Omniverse enables interactive\, multi-user digi
 tal worlds that help teams explore\, understand and act on complex informa
 tion more quickly. We present our approach to integrating user tools and d
 ata sources with OpenUSD\, and how we leverage Omniverse experiences of ou
 r fusion research facilities to combine live data streams\, fast simulatio
 n predictions and rich 3D context. The result is a composable framework fo
 r building actionable digital twin applications that accelerate insight\, 
 improve cross-domain communication and support faster\, better-informed de
 cision-making.\n\nhttps://indico.ukaea.uk/event/862/
URL:https://indico.ukaea.uk/event/862/
END:VEVENT
END:VCALENDAR