Skip to content

Data Fusion Labeler (dFL)

The Data Fusion Labeler (dFL) is a web-based tool for interactively labeling and curating fusion datasets. Built on top of TokSearch and CMF, dFL lets researchers browse shot-by-shot diagnostics, tag interesting events (like disruptions or ELMs), and export versioned, labeled datasets for downstream analysis or machine learning.

What It’s For

  • Interactive exploration of fusion data
  • Manual tagging of disruptions, regimes, or diagnostic features
  • Creating labeled datasets for ML training
  • Curation of campaign-specific or topic-specific shot selections

dFL supports multi-signal visualizations, metadata overlays, and integration with CMF for saving labels as versioned, shareable artifacts. It’s tightly integrated with the Fusion Data Platform and designed to work seamlessly with TokSearch pipelines and cached data.

Features

  • Interactive plotting of diagnostic time series
  • Multi-shot navigation and comparison
  • Custom label definitions and schema support
  • Export to CMF repositories for traceable reuse

Coming Soon

The dFL interface will be made publicly available as part of an upcoming platform release. Until then, it is in active use for internal curation tasks within the FDP project.

Need a disruption-tagged dataset for ML? Want to curate examples of a rare operating mode? dFL gives you the tools to explore, label, and publish clean, consistent datasets—without leaving the platform.