Speaker
Description
The LEGEND experimental program will operate in two phases to search for neutrinoless double-beta decay ($0\nu\beta\beta$). The first (second) stage will employ 200 (1000) kg of $^{76}$Ge semiconductor detectors to achieve a half-life sensitivity of 10$^{27}$ (10$^{28}$) years. In this study, we present a data-driven approach to remove electronic noise, cross-talk, and non-physical events captured by $^{76}$Ge detectors in LEGEND powered by a novel artificial intelligence model. We first de-noise and extract waveform shape information via a Discrete Wavelet Transform (DWT). We then utilize an unsupervised learning clustering algorithm called Affinity Propagation (AP) to obtain a representative waveform basis for a given dataset. Finally, we expand the results we obtain from AP to larger datasets with a Support Vector Machine (SVM). We demonstrate that our model is efficient at classifying events for low-background datasets obtained in early detector tests performed before the full-scale construction of LEGEND-200. This method will enable for the automatic detection and removal of non-physical events, which requires significant time and human effort in traditional data cleaning.
*This work is supported by the U.S. DOE, and the NSF, the LANL, ORNL and LBNL LDRD programs; the European ERC and Horizon programs; the German DFG, BMBF, and MPG; the Italian INFN; the Polish NCN and MNiSW; the Czech MEYS; the Slovak SRDA; the Swiss SNF; the UK STFC; the Russian RFBR ; the Canadian NSERC and CFI; the LNGS and SURF facilities.
