ABU DHABI (ALETIHAD)
Researchers at New York University Abu Dhabi (NYUAD) have demonstrated that artificial intelligence can independently rediscover fundamental principles of particle physics, a breakthrough that could accelerate future discoveries about the universe’s underlying laws.
In a study published in the Journal of High Energy Physics (JHEP), NYU Abu Dhabi scientists showed that relatively simple AI techniques can uncover the same patterns that took human physicists decades to identify during the development of the Standard Model, the framework that describes the fundamental particles and forces of nature.
The research team, Aya Abdelhaq, Pellegrino Piantadosi, and Fernando Quevedo, used experimental data from particle discoveries of the 1950s and 1960s. Without prior knowledge of the mathematical tools used at the time, the AI system identified organising principles behind dozens of particles.
"This study shows that AI can uncover deep physical laws directly from data, opening the door to discovering new particles and patterns that humans may have missed,” said Pellegrino Piantadosi, NYUAD postdoctoral associate and one of the paper’s authors.
Among the rediscovered features were fundamental symmetries such as baryon number, isospin, and charm, as well as the “Eightfold Way,” a classification scheme that groups particles into structured families. The AI also reproduced Regge trajectories, patterns that relate a particle’s mass to its spin and closely match experimental observations.
The Standard Model emerged over decades through theoretical insight and experimental breakthroughs, including the discovery of quarks, the building blocks of protons and neutrons inside atomic nuclei. Showing that AI can reach similar conclusions using data alone highlights its potential as a powerful tool for scientific discovery.
Artificial intelligence is already transforming research across disciplines. Demonstrating that AI can reconstruct major past discoveries is an important step toward using it to uncover new particles or previously unknown patterns in nature, NYU Abu Dhabi said in a statement. The findings suggest that future AI systems could help identify unseen phenomena and deepen our understanding of the fundamental laws that govern the universe.