Speaker
Description
In the Standard Model, neutrinos are predicted to have zero mass. However, the discovery of neutrino oscillations has proven that neutrinos possess mass, making neutrino research a promising avenue for exploring Beyond the Standard Model (BSM) physics. Detectors designed to track particles such as neutrinos operate by utilizing interactions between the particles and the detector material. Determining the precise vertex location of these interactions is a key factor in optimizing the detection efficiency of the detector. Traditionally, the estimation of primary particle interaction points (vertices) within detectors has relied on human-centric, cut-based analyses. However, such methods often struggle to obtain sufficient information for accurate interpretation, due to the detector structures. Waveform data contain a wealth of information, including signals that undergo multiple reflections and refractions. However, traditional analysis methods face challenges in effectively extracting meaningful features from these intricate waveforms. Recent advancements in computational technologies have accelerated the integration of modern techniques such as simulations and artificial intelligence (AI) into such complex analyses. AI has demonstrated remarkable capabilities in recognizing patterns from large and complex datasets, which are often difficult for human analysis. This poster presents the potential of AI for vertex reconstruction, utilizing results from Monte Carlo (MC) simulations, DAQ simulations, and signals from a wave generator.
