Nabila Majeed

My research:

I’m studying neutrino interactions using MicroBooNE, with a focus on understanding complex event topologies involving multiple pions and protons. This work helps improve models of neutrino-nucleus interactions, which are crucial for long-baseline experiments like DUNE.

My expertise is:

I specialize in machine learning and AI, applying these tools to particle physics problems. This includes event classification, signal/background separation, and feature-based modeling of detector responses or interaction processes.

A problem I’m grappling with:

I’m working on disentangling overlapping physics processes—specifically, how to tell resonance from deep inelastic scattering when both can produce similar final states. The difficulty lies in subtle differences in event structure that aren’t always easy to capture with traditional methods.

I’ve got my eyes on:

I’m exploring ways to improve physics model discrimination, incorporate more data-driven techniques, and use ML not just for selection but also to gain insight into what drives different interaction types.

I want to know more about:

I want to better understand how modern ML can complement physics-based modeling, especially in areas like uncertainty quantification, model interpretability, and cross-section extraction workflows.