DOE Announces $ 5.7 Million in AI and ML Research for Accelerators and Detectors for Nuclear Physics

December 2, 2021 – The U.S. Department of Energy (DOE) today announced $ 5.7 million for six projects that implement artificial intelligence methods to accelerate scientific discoveries in nuclear physics research. The projects aim to optimize the overall performance of complex accelerator and detector systems for nuclear physics with the help of advanced computational methods.

“Artificial intelligence has the potential to shorten the time frame for experimental discoveries in nuclear physics,” said Timothy Hallman, DOE associate director of Science for Nuclear Physics. “Particle accelerators and nuclear physics instruments face a multitude of technical challenges in simulations, control, data acquisition and analysis that artificial intelligence promises to overcome.”

The six projects are carried out by nuclear physics researchers at five national DOE laboratories and four universities. Projects include developing deep learning algorithms to identify a unique signal for a suspected, very slow core process known as neutrino-less double beta decay. This decay, if observed, would be at least ten thousand times rarer than the rarest known nuclear decay and could show how our universe was dominated by matter rather than antimatter. Supported efforts also include an AI-driven detector design for the Electron-Ion Collider Accelerator project under construction at Brookhaven National Laboratory, which will study the internal structure and forces of protons and neutrons that make up the atomic nucleus.

The projects are supported by the DOE Office of Science Nuclear Physics Program. The prizes were selected through competitive peer review. Total projected funding is $ 5.7 million, with $ 3.2 million earmarked for fiscal 2021 and funding beyond the year depending on congressional funds. The list of projects and further information can be found here.

Source: Department of Energy