Physics PhD student in experimental neutrino physics at Florida State University, currently a URA Visiting Scholar at Fermilab. I work on machine learning for particle identification and build software tools for large-scale detector data analysis on the NOvA and DUNE-ND neutrino experiments.
- Neutron detection in NOvA — data-driven algorithms to detect rare delayed neutron-capture signals in large-scale detector data, and simulation-to-data correction models that reduced systematic prediction bias by 20%.
- Neutron tagging in DUNE-ND (2x2 prototype) — deep learning models to identify neutron-induced signals in high-granularity sensor data, with simulation-driven labeling and feature-extraction pipelines for sparse spatiotemporal data.
- Reconstructed_Neutrons_Analyzer — Prong-level neutron-signal reconstruction for NOvA: purity/efficiency studies and two interactive Flask viewers (3D event display, muon-cylinder cut scanner).
- Neutron_Spectrums — CAFAna macros producing neutron kinematic spectra by event topology and hadronic visible energy, for FHC/RHC beam configurations.
- DataAnalyzer_2x2 — Neutron tagging from neutrino interactions in the DUNE-ND 2x2 prototype: neutrino/proton/neutron selection pipeline, efficiency/purity characterization, and Python tools for CAF-derived data.
Machine learning: neural networks, deep learning, classification / particle-identification models, model evaluation & validation, AI-assisted tool development Data analysis: ROOT, NumPy, pandas, Jupyter, Mathematica Other: G4beamline, SolidWorks, Arduino
- PhD, Physics — Florida State University (2022–present)
- B.S., Physics — Simon Bolivar University, Caracas, Venezuela (2015–2021)
- CERN Summer Student, Geneva (2019) — studied particle production in the K12 beam line for different Geant4 physics lists. Report · Talk
Chicago, IL