As cryogenic detectors push toward ever-lower energy thresholds, their sensitivity is increasingly constrained by a persistent low energy background known as the low energy excess (LEE). We report observation of LEE in the MINER experiment using a sapphire ($\mathrm{A}{\mathrm{l}}_2{\mathrm{O}}_3$) detector at energies around 200 eV, with the excess reproducibly reappearing after each nonoperational warm-up period. To address this limiting background, we implement an unsupervised convolutional variational autoencoder framework that identifies anomalous events through a reconstruction-based anomaly score. For the first time in a pulse-shape driven analysis, we uncover a significant deviation in the rise-time of LEE events relative to Monte Carlo simulated ideal signals. Using this feature, we develop a discrimination pipeline based on rise-time selection. This method achieves up to 53% rejection of LEE events, corresponding to an expected sensitivity improvement of nearly 10% for MINER at HFIR. These findings are consistent with a scenario in which a subset of the observed LEE events may be associated with bulk-related processes, such as crystal defects or microfractures within the detector crystal, although additional detector-related mechanisms may also play a role. Our result provides a powerful, data-driven pathway for mitigating LEE and enhancing the discovery potential of next-generation cryogenic experiments.

Close

PrevNext

View figure in article

• Neutrino interactions
• Nucleus-neutrino interactions
• Machine learning
• Neutrino detection