Calorimeter Image Datasets for the Standard Model at the LHC

University of Cambridge researcher C. G. Lester provides calorimeter image datasets for particle physics. The data consists of simulated calorimeter images stored as arrays with shape (n, 32, 32) corresponding to event index and unrolled eta-phi coordinates. The dataset is split into training, validation, and testing batches.

Use Cases

• Train anomaly detection models for rare particle physics events based on calorimeter image data.
• Develop and benchmark computer vision classifiers for standard model processes using the provided image splits.
• Validate simulation-to-real performance for LHC event reconstruction based on the unrolled eta-phi surface representation.

Strengths

• Data is pre-split into independent training, validation, and testing sets, facilitating machine learning workflows.
• Images are stored in a standardized HDF5 format under a consistent key, easing programmatic access.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

C. G. Lester, University of Cambridge

Collection Method

Simulated data generated for the described paper on parity violation.