Plate Nº 27 · recorded October 10, 2026
PhysicsReported finding
Nobel physics winner Halzen credits early AI push in neutrino work
Francis Halzen, the 82-year-old University of Wisconsin-Madison physicist behind the IceCube neutrino observatory, won the 2026 Nobel Prize in physics and credits a 1991 paper proposing AI for data analysis.
By Nathan Brooks3 min read569 words
In brief
- Francis Halzen, 82, won the 2026 Nobel Prize in physics for his work on the IceCube neutrino observatory.
- IceCube uses 5,484 optical sensors buried more than a kilometer deep in Antarctic ice.
- Halzen published a 1991 paper proposing AI for analyzing physics experiment data, among the earliest such uses.
- Modern neural networks allowed IceCube to extract the Milky Way's neutrino signal, which had eluded earlier analyses.
- The U.S. National Science Foundation has provided roughly $250 million (about €224 million) for IceCube.
IceCube's 5,484 sensors help Halzen claim a Nobel
Francis Halzen, 82, holds one of the 2026 Nobel Prizes in physics. The U.S.–Belgian physicist spoke with reporters in Turin, Italy, on Wednesday, a day after the announcement from Stockholm.
Halzen built and leads the IceCube neutrino observatory at the South Pole. The instrument strings 5,484 optical sensors more than a kilometer deep into Antarctic ice. When neutrinos — rare, nearly massless subatomic particles streaming from distant cosmic events — collide with ice atoms, they produce faint flashes that the sensors record.
What did Halzen do with AI back in 1991?
Halzen traced his AI involvement to three decades ago.
"In fact, the first neural nets appeared in the late 1980s, and I am very proud that I wrote a paper in 1991 proposing to use AI to analyze the data of part of the classical physics experiment," he said.
Neural networks are computer programs that try to mimic how the brain recognizes patterns in data. Halzen's team ran them on IceCube data on and off for years, mostly without dramatic results.
"We kind of used neural nets occasionally. And that changed a few years ago, when these very powerful neural nets came along," he said.
The breakthrough came from modern deep-learning tools that can sift signal from noise in the observatory's huge datasets.
Why does the Milky Way matter here?
Halzen described a problem that puzzled his team for nearly a decade. IceCube watches the entire sky through neutrinos rather than light, and the two views do not match.
"When you look at the sky normally, you see the Milky Way. But when you look at the sky of neutrinos, you see other galaxies, you don't see the Milky Way," Halzen said.
Modern neural networks finally fixed that gap.
"It was only after we used neural nets and machine learning techniques that we finally began to see the Milky Way in our data, which we now have extracted convincingly," he said.
In plain terms: standard astronomy sees our galaxy glowing brightly. Neutrino astronomy, until recently, did not. New AI tools pulled the Milky Way's neutrino signal out of years of background noise.
How much has the project cost so far?
The U.S. National Science Foundation has provided roughly $250 million (about €224 million) for IceCube over the project's lifetime. Halzen said he is drafting a new proposal and hopes the Nobel announcement helps it land.
What does the award say about basic research?
Antonio Zoccoli, president of Italy's National Institute for Nuclear Physics and a Halzen collaborator, framed the prize as a defense of curiosity-driven science at a moment when applied research attracts most of the attention.
The Nobel announcement, Zoccoli said, is "clear recognition of the importance of fundamental research" for "understanding our nature and our origins."
Can physicists still do this kind of work?
Halzen warned that funding pressure is real. "Doing science is more difficult" because of budget issues, he said, although "universities are surviving."
He added that he is the "wrong person" to detail the cuts, because IceCube itself was spared.
What about the childhood dream?
Asked whether he had long imagined a Nobel, Halzen — raised in Belgium — offered a different fantasy.
"I'm from Belgium, I wanted to win the Tour de France," he joked.
The Nobel, he suggested, will have to do.
via Phys.org Physics (Source)
More from Nathan Brooks
Nearby plates
- Francis Halzen wins Nobel Prize in Physics for IceCube neutrino work
- Google DeepMind Embeds Invisible Watermarks in AI-Designed Proteins
- AI Scientist Makes Biological Discoveries With Minimal Human Help
- Uranium Compound Known Since the 1960s Hides a Spiral Structure
- First Real-Time Observation of Sound Making Quantum Jumps