麻豆官网

麻豆官网鈥檚 Abhirami Harilal is helping physicists hunt for new particles that could unlock one of the universe鈥檚 biggest mysteries: dark matter.

During her four years at CERN, Harilal used machine learning to improve how physicists detect rare particle signatures, which has sharpened the Large Hadron Collider鈥檚 search. Along the way, she also upgraded CERN鈥檚 detector technology by developing algorithms now deployed inside the Compact Muon Solenoid (CMS) experiment to autonomously identify anomalies more accurately than ever before.

鈥淭here are still many fundamental questions about the universe that current physics can鈥檛 fully explain,鈥� said Harilal, who graduated from Carnegie Mellon with a Ph.D. in physics. 鈥淎t the Large Hadron Collider, we鈥檙e searching for signs of new particles that could help answer them.鈥�

Only about 5 percent of the universe is made of matter, which people can see with their own eyes or detect using scientific equipment. The rest of the universe consists largely of dark matter and dark energy, which researchers are unable to observe through traditional methods. Though these forces are unseen, they affect the movement of galaxies, stars and planets.

Researchers at CERN are working to understand what these particles are and how they behave. In 2012, they discovered the Higgs boson, a particle that represents the physical manifestation of a quantum field permeating the universe.

鈥淭he Higgs boson takes a very special role in what we know about fundamental particles, and many theories suggest that if new particles exist, they could be connected to the Higgs boson,鈥� Harilal said. 鈥淚 was trying to see if this Higgs boson would give way or decay into a new particle called an A particle, which could be connected to dark matter or other hidden sectors.鈥�

Harilal used machine learning models to improve how researchers detect the A particle. She used computational modeling to simulate thousands of particle collisions similar to those produced at the LHC. Using these methods, Harilal improved the experiment鈥檚 sensitivity to particles with unusual or hard-to-detect signatures, including potentially the A particle.

In addition to conducting her own research, Harilal also improved CERN鈥檚 CMS detector using similar machine learning methods. When Harilal first arrived at CERN, the detector鈥檚 data monitoring system could flag unusual activity in the data but had criteria that could miss subtle or changing anomalies. Researchers often had to manually compare the flagged data known, reliable datasets to pinpoint the anomalies.

Harilal developed a machine learning model to automate the process, not only alerting the researchers to unusual activity but also identifying how the data differed from expected results. Her work has made it easier for CERN scientists to diagnose potential issues as they gather data.

鈥淚鈥檓 particularly proud about it because this was actually deployed and used during live data taking,鈥� Harilal said.

Harilal's advisor Manfred Paulini, professor of physics and Mellon College of Sciences Associate Dean for Research, said Harilal鈥檚 work helped make progress both in physics and in machine learning.

鈥淚 feel very fortunate to work with exceptional graduate students like Abhirami, who are not only experts in particle physics research but also operate at the forefront of developing machine learning algorithms,鈥� Paulini said. 鈥淭hroughout her Ph.D. in high energy physics, Abhirami cultivated a broad set of technical and professional skills that are directly transferable to solving real-world challenges.鈥�

Harilal is assisting other projects related to the CMS from Pittsburgh. Once she is done with her research, she said she hopes to apply her machine learning skills to other areas in research or industry.

鈥淎 big part of my work is recognizing meaningful patterns in large amounts of noisy data, which is also relevant in many other applications,鈥� Harilal said. 鈥淪imilar ideas apply in areas like medical imaging, financial data, drug discovery. I鈥檓 looking forward to finding other opportunities to use these skills.鈥�

Related Content

MCS Students Earn NSF Graduate Research Fellowships

Kyungmin Park Accelerates CMS Trigger Work at CERN