We are developing a unified AI foundation model that learns from data across the different detector technologies used in neutrinoless double-beta decay experiments. This shared framework will streamline data analysis, transfer knowledge across experiments, and accelerate the search for this extremely rare process. The project was selected for the U.S. Department of Energy's inaugural Genesis Mission.
We are developing machine learning algorithms to be deployed on FPGAs within the KamLAND2-Zen DAQ system, enabling real-time data processing at the experiment's front end.
We are developing a new DAQ system for the COHERENT detectors based on the RFSoC platform. The system uses the RF ADC to directly digitize detector signals and deploys machine learning algorithms on the RFSoC programmable logic to achieve real-time data processing.
My work includes the development and optimization of particle detection systems, with a particular focus on cryogenic detectors.