Fast machine learning trigger system for real-time event identification for Ba-tagging
ORAL
Abstract
A next-generation neutrinoless double beta decay (0νββ) search in ¹³⁶Xe has the potential to discover lepton number violation, and determine if neutrinos are their own antiparticles. If observed, this rare decay would demonstrate physics beyond the Standard Model and provide key insights into matter formation in the Universe.
Fast machine learning allows real time data processing in hardware, enabling rapid and intelligent triggers for particle physics experiments. At UC San Diego, our group is developing a Ba-tagging technique to increase the sensitivity in future searches of 0νββ by probing the decay volume for the presence of the ¹³⁶Xe decay daughter, ¹³⁶Ba. We work on a low-latency convolutional neural network that is capable of identifying candidate 0νββ events using FPGA hardware. This enables fast triggering and real-time decision making during detector operation. By applying this procedure to simulated charge and light waveforms, we aim to perform rapid vertex reconstruction, energy estimation, and background discrimination. If a potential signal is found, a cryogenic probe will extract and analyze the ¹³⁶Ba daughter through laser spectroscopy in solid xenon. Introducing fast ML into the Ba-tagging technique will create an intelligent and efficient trigger for 0νββ decay searches.
Fast machine learning allows real time data processing in hardware, enabling rapid and intelligent triggers for particle physics experiments. At UC San Diego, our group is developing a Ba-tagging technique to increase the sensitivity in future searches of 0νββ by probing the decay volume for the presence of the ¹³⁶Xe decay daughter, ¹³⁶Ba. We work on a low-latency convolutional neural network that is capable of identifying candidate 0νββ events using FPGA hardware. This enables fast triggering and real-time decision making during detector operation. By applying this procedure to simulated charge and light waveforms, we aim to perform rapid vertex reconstruction, energy estimation, and background discrimination. If a potential signal is found, a cryogenic probe will extract and analyze the ¹³⁶Ba daughter through laser spectroscopy in solid xenon. Introducing fast ML into the Ba-tagging technique will create an intelligent and efficient trigger for 0νββ decay searches.
*This work was supported by the DOE Office of Science (Office of Nuclear Physics) and the Secretariat of Science, Humanities, Technology, and Innovation of Mexico (SECIHTI)
–
Presenters
-
Melissa Medina-Peregrina
- University of California, San Diego