MagicTelescope: Simulated Gamma-Ray Particle Events for Signal Classification

MagicTelescope is a dataset for classification on numerical features, used in a tabular data benchmark. The data were generated by a Monte Carlo program (Corsika) to simulate the registration of high-energy gamma particles in a ground-based atmospheric Cherenkov gamma telescope. The dataset was donated by P. Savicky from the Institute of Computer Science, AS of CR, Czech Republic, and originates from the MAGIC (Major Atmospheric Gamma Imaging Cherenkov) Telescope project.

Use Cases

• Binary classification of gamma-ray signals from hadronic background based on simulated shower image parameters.
• Benchmarking tabular classification algorithms on numerical features derived from physical event data.
• Feature engineering and analysis of ellipse (Hillas) parameters for particle discrimination in telescope imagery.

Strengths

• Data is generated via a documented Monte Carlo simulation (Corsika), providing a controlled benchmark environment.
• Dataset is part of a published tabular data benchmark, suggesting a standardized transformation and evaluation context.
• Original research and methodology are cited, providing traceability to the scientific publication.

Limitations

• Row count, column definitions, and file formats are unknown, which limits suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

UCI Machine Learning Repository, originally from the MAGIC Telescope project.

Collection Method

Monte Carlo simulation using the Corsika code.