Doctoral candidate Nina Andrejevic combines spectroscopy and machine studying methods to establish novel and beneficial properties in matter.
Born right into a household of architects, Nina Andrejevic liked creating drawings of her house and different buildings whereas a toddler in Serbia. She and her twin sister shared this ardour, together with an urge for food for math and science. Over time, these pursuits converged right into a scholarly path that shares some attributes with the household career, in response to Andrejevic, a doctoral candidate in supplies science and engineering at MIT.
“Structure is each a inventive and technical subject, the place you attempt to optimize options you need for sure sorts of performance, like the dimensions of a constructing, or the structure of various rooms in a house,” she says. Andrejevic’s work in machine studying resembles that of architects, she believes: “We begin from an empty web site — a mathematical mannequin that has random parameters — and our objective is to coach this mannequin, referred to as a neural community, to have the performance we want.”
Andrejevic is a doctoral advisee of Mingda Li, an assistant professor within the Division of Nuclear Science and Engineering. As a analysis assistant in Li’s Quantum Measurement Group, she is coaching her machine-learning fashions to hunt for brand new and helpful traits in supplies. Her work with the lab has landed in such main journals as Nature Communications, Superior Science, Bodily Evaluation Letters, and Nano Letters.
MIT doctoral candidate Nina Andrejević (proper) has developed along with her twin sister Jovana (left), a PhD candidate at Harvard College, a technique for testing materials samples to foretell the presence of topological traits that's quicker and extra versatile than different strategies. Credit score: Gretchen Ertl
One space of particular curiosity to her group is that of topological supplies. “These supplies are an unique section of matter that may transport electrons on the floor with out power loss,” she says. “This makes them extremely attention-grabbing for making extra energy-efficient applied sciences.”
Along with her sister Jovana, a doctoral candidate in utilized physics at Harvard College, Andrejevic has developed a technique for testing materials samples to foretell the presence of topological traits that's quicker and extra versatile than different strategies.
If the last word objective is “producing better-performing, energy-saving applied sciences,” she says, “we should first know which supplies make good candidates for these purposes, and that’s one thing our analysis might help verify.”
Teaming up
The seeds for this analysis had been planted greater than a yr in the past. “My sister and I at all times mentioned it could be cool to do a venture collectively, and when Mingda prompt this examine of topological supplies, it occurred to me that we may make this a proper collaboration,” says Andrejevic. The sisters are extra related than most twins, she notes, sharing many tutorial pursuits. “Being a twin is a large a part of my life and we work collectively effectively, serving to one another in areas we don’t perceive.”
Andrejevic’s dissertation work, which encompasses a number of tasks, makes use of specialised spectroscopic methods and information evaluation, bolstered by machine studying, which may discover patterns in huge quantities of information extra effectively than even probably the most high-throughput computer systems.
When she graduates this winter, Nina Andrejević will head to Argonne Nationwide Laboratory, the place she plans to concentrate on designing physics-informed neural networks. Credit score: Gretchen Ertl
“The unifying thread amongst all my tasks is this concept of attempting to speed up or enhance our understanding when making use of these characterization instruments, and to thereby receive extra helpful data than we will with extra conventional or approximate fashions,” she says. The twins’ analysis on topological supplies serves as a working example.
So as to tease out novel and probably helpful properties of supplies, researchers should interrogate them on the atomic and quantum scales. Neutron and photon spectroscopic methods might help seize beforehand unidentified constructions and dynamics, and decide how warmth, electrical or magnetic fields, and mechanical stress have an effect on supplies on the Lilliputian degree. The legal guidelines governing this realm, the place supplies don't behave as they may on the macro-scale, are these of quantum mechanics.
Present experimental approaches to figuring out topological supplies are difficult technically and inexact, probably excluding viable candidates. The sisters believed they may keep away from these pitfalls utilizing a broadly utilized imaging approach, referred to as X-ray absorption spectroscopy (XAS), and paired with a educated neural community. XAS sends targeted X-ray beams into matter to assist map its geometry and electron construction. The radiation information it offers presents a signature distinctive to the sampled materials.
“We needed to develop a neural community that might establish topology from a fabric’s XAS signature, a way more accessible measurement than that of different approaches,” says Andrejevic. “This might hopefully permit us to display screen a wider class of potential topological supplies.”
Over months, the researchers fed their neural community data from two databases: one contained supplies theoretically predicted to be topological, and the opposite contained X-ray absorption information for a broad vary of supplies. “When correctly educated, the mannequin ought to function instrument the place it reads new XAS signatures it hasn’t seen earlier than, and tells if you happen to if the fabric that produced the spectrum is topological,” Andrejevic explains.
The analysis duo’s approach has demonstrated promising outcomes, which they've already revealed in a preprint, “Machine studying spectral indicators of topology.” “For me, the joys with these machine-learning tasks is seeing some underlying patterns and with the ability to perceive these when it comes to bodily portions,” says Andrejevic.
Shifting towards supplies research
It was throughout her first yr at Cornell College that Andrejevic first skilled the pleasure of peering at matter on an intimate degree. After a course in nanoscience and nanoengineering, she joined a analysis group imaging supplies on the atomic scale. “I really feel I’m a really visible particular person, and this concept of with the ability to see issues that as much as that time had been simply equations or ideas — that was actually thrilling,” she says. “This expertise moved me nearer to the sphere of supplies science.”
Machine studying, pivotal to Andrejevic’s doctoral work, will likely be central to her life after MIT. When she graduates this winter, she heads straight for Argonne Nationwide Laboratory, the place she has received a prestigious Maria Goeppert Mayer Fellowship, awarded “internationally to excellent doctoral scientists and engineers who're at early factors in promising careers.” “We’ll be attempting to design physics-informed neural networks, with a concentrate on quantum supplies,” she says.
It will imply saying goodbye to her sister, from whom she has by no means been separated for lengthy. “It will likely be very totally different,” says Andrejevic. However, she provides, “I do hope that Jovana and I'll collaborate extra sooner or later, regardless of the space!”
Post a Comment