Relatore
Descrizione
The search for neutrinoless double beta decay is crucial to shed light on neutrino properties and broader cosmological questions. Experiments utilizing the isotope 76Ge have been essential in advancing the sensitivity to neutrinolsess double beta decay. The LEGEND project uses High Purity Germanium (HPGe) detectors and minimize background interference through the application of Pulse Shape Analysis (PSA) significantly. To further refine this process, we tested the adoption of a Neural Network enhanced by Feature Importance Supervision (FIS) adjusted for PSA in HPGe detectors. This approach integrates expert knowledge on waveform characteristics, enabling the model to tag signal from background noise without energy dependence. It has demonstrated considerable success in differentiating between the multi-site gamma radiation that forms
background noise and the single-site signals indicative of neutrinoless double beta decay. In this poster, I will present the current status of the approach under development.
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, SNOLAB, and SURF facilities.
| Poster prize | No |
|---|---|
| Given name | Katharina |
| Surname | Kilgus |
| First affiliation | Eberhard Karls Universität Tübingen |
| Institutional email | katharina.kilgus@uni-tuebingen.de |
| Gender | Prefer not to answer |
| Collaboration (if any) | LEGEND Collaboration |
