Skip to content

Latest commit

 

History

History
9 lines (6 loc) · 708 Bytes

File metadata and controls

9 lines (6 loc) · 708 Bytes

Feature: Machine learning interface for direction reconstruction

  • Adds an interface to run machine learning models (e.g., scikit-learn).
  • Provides an example using XGBoost regression trees to estimate directions in camera coordinates.
  • Introduces a Python environment and a scripts directory to support training and inference.

The new XGBoost-based training and reconstruction methods estimate the gamma‑ray arrival direction in camera coordinates. They support DispBDT and intersection methods, combining image parameters to compute Xoff/Yoff.

Compared to previous approaches that averaged over all DispBDT directions, this implementation better handles edge cases (e.g., truncated images).