Published recently within the NJ Computational Materials journal, the study was headed by physicist and engineer, Sanghamitra Neogi. In their new study, Neogi and her collaborators plotted the physics of small building blocks composed of atoms and subsequently applied machine learning methods to predict the behavior of larger structures produced from those small building blocks. it’s quite like watching a solo Lego brick to predict the strength of a comparatively larger castle. This quest may benefit the electronics that underpin our day-to-day lives, from electric cars and smartphones to emerging quantum computers. consistent with Neogi, engineers could someday use the researchers’ techniques to pinpoint the weak points within the design of electrical components beforehand.
The study may be a part of Neogi’s broader view of how the realm of very small things, just like the wiggling of atoms, can help build new computers that are more efficient or maybe computers that are inspired by human brains. The study was co-authored by Artem Pimachev, a search associate in aerospace engineering at CU Boulder. Neogi’s latest study targets an enormous liability within the electronics sector, that is, hotspots, but this doesn’t mean mobile WiFi hookups. Neogi elaborated that a majority of the newest computing tools have many imperfections — small flaws in electronic components can cause the warmth to accumulate at specific sites, almost like a bicycle slowing down when it goes over rough terrain. These “hotspots” also can make smartphones much less efficient.
According to Neogi, the difficulty is that engineers inspired by computer models, or simulations, find it difficult to predict the looks of these weak points beforehand. Neogi believes that machine intelligence can help scientists develop more improved electronics. Imagine those individual Lego bricks, which, during this example, are clumps of 16 germanium and silicon atoms — the key ingredients in several computer components. In the latest analysis, Neogi and her collaborators have designed a computer model that utilizes AI to find out the physical characteristics inside those building blocks — or how electrons and atoms combine to work out the energy landscape inside a cloth. Subsequently, the model can extrapolate from those fundamental blocks to predict energy distribution in relatively larger pieces of atoms.
“It collects information from each individual unit and combines them to predict the ultimate properties of the collective system, which may be made from two, three, or more units,” added Neogi. Neogi’s research still features a great distance to travel before they will determine all the possible weak points during a device, almost like the dimensions of a phone. However, up so far, the new model has shown to be effective. Neogi and her collaborators have used this tool to exactly predict the characteristics of the many real-world materials made up of germanium and silicon. Neogi is additionally drawing on her knowledge to find out how heat and energy flow at very small scales to not only enhance present-day devices but also help produce futuristic devices.
In 2019, Neogi was involved during a $1.7 million national effort to review the potential for “neuromorphic” computers, or devices that store and inspect data by emulating the activity of the brain’s neurons. “What I would like to try to nudge this world of atoms in your handheld device and understand how materials and electronics close to form a tool work,” concluded Neogi. Neogi, S & Pimachev, A K (2021) First-principles prediction of electronic transport in fabricated semiconductor heterostructures via physics-aware machine learning.