Artificial intelligence breaks the ice with quantum accuracy In simulation
| | | | |

Artificial intelligence breaks the ice with quantum accuracy In simulation

A team based at Princeton University has accurately simulated the initial steps of ice formation by applying artificial intelligence (AI) to solving equations that govern the quantum behavior of individual atoms and molecules.

The resulting simulation describes how water molecules transition into solid ice with quantum accuracy. This level of accuracy, once thought unreachable due to the amount of computing power it would require, became possible when the researchers incorporated deep neural networks, a form of artificial intelligence, into their methods. The study was published in the journal Proceedings of the National Academy of Sciences.

“In a sense, this is like a dream come true,” said Roberto Car, Princeton’s Ralph W. *31 Dornte Professor in Chemistry, who co-pioneered the approach of simulating molecular behaviors based on the underlying quantum laws more than 35 years ago. “Our hope then was that eventually we would be able to study systems like this one, but it was not possible without further conceptual development, and that development came via a completely different field, that of artificial intelligence and data science.”

The ability to model the initial steps in freezing water, a process called ice nucleation, could improve accuracy of weather and climate modeling as well as other processing like flash-freezing food.

Researchers at Princeton University combined artificial intelligence and quantum mechanics to simulate what happens at the molecular level when water freezes. The result is the most complete yet simulation of the first steps in ice “nucleation,” a process important for climate and weather modeling. Credit: Pablo Piaggi, Princeton University
The new approach enables the researchers to track the activity of hundreds of thousands of atoms over time periods that are thousands of times longer, albeit still just fractions of a second, than in early studies.

Car co-invented the approach to using underlying quantum mechanical laws to predict the physical movements of atoms and molecules. Quantum mechanical laws dictate how atoms bind to each other to form molecules, and how molecules join with each other to form everyday objects.

Car and Michele Parrinello, a physicist now at the Istituto Italiano di Tecnologia in Italy, published their approach, known as “ab initio” (Latin for “from the beginning”) molecular dynamics, in a groundbreaking paper in 1985.

But quantum mechanical calculations are complex and take tremendous amounts of computing power. In the 1980’s, computers could simulate just a hundred atoms over spans of a few trillionths of a second. Subsequent advances in computing and the advent of modern supercomputers boosted the number of atoms and timespan of the simulation, but the result fell far short of the number of atoms needed to observe complex processes such as ice nucleation.

AI provided an attractive potential solution. Researchers train a neural network, named for its similarities to the workings of the human brain, to recognize a comparatively small number of selected quantum calculations. Once trained, the neural network can calculate the forces between atoms that it has never seen before with quantum mechanical accuracy. This “machine learning” approach is already in use in everyday applications such as voice recognition and self-driving automobiles.

In the case of AI applied to molecular modeling, a major contribution came in 2018 when Princeton graduate student Linfeng Zhang, working with Car and Princeton professor of mathematics Weinan E, found a way to apply deep neural networks to modeling quantum-mechanical interatomic forces. Zhang, who earned his Ph.D. in 2020 and is now a research scientist at the Beijing Institute of Big Data Research, called the approach “deep potential molecular dynamics.”

In the current paper, Car and postdoctoral researcher Pablo Piaggi along with colleagues applied these techniques to the challenge of simulating ice nucleation. Using deep potential molecular dynamics, they were able to run simulations of up to 300,000 atoms using significantly less computing power, for much longer timespans than were previously possible. They carried out the simulations on Summit, one of the world’s fastest supercomputers, located at Oak Ridge National Laboratory.

This work provides one of the best studies of ice nucleation, said Pablo Debenedetti, Princeton’s dean for research and the Class of 1950 Professor of Engineering and Applied Science, and a co-author of the new study.

“Ice nucleation is one of the major unknown quantities in weather prediction models,” Debenedetti said. “This is a quite significant step forward because we see very good agreement with experiments. We’ve been able to simulate very large systems, which was previously unthinkable for quantum calculations.”

Currently, climate models obtain estimates of how fast ice nucleates primarily from observations made in laboratory experiments, but these correlations are descriptive, not predictive, and are valid over a limited range of experimental conditions. In contrast, molecular simulations of the type done in this study can produce simulations that are predictive of future situations, and can estimate ice formation under extreme conditions of temperature and pressure, such as on other planets.

Water molecules consist of two hydrogen atoms and an oxygen atom. The electrons around each atom determine how atoms can bond with each other to form molecules.

The atoms can exist in literally millions of different arrangements, said Car, who is director of the Chemistry in Solution and at Interfaces center, funded by the U.S. Department of Energy Office of Science and including regional universities.

“The magic is that because of some physical principles, the machine is able to extrapolate what happens in a relatively small number of configurations of a small collection of atoms to the countless arrangements of a much bigger system,” Car said.

사이언스모니터 뉴스레터
AI·양자·R&D 핵심 해설을 주 2회(화·금) 이메일로 받아 보세요.

Similar Posts

  • | | | | |

    최초의 단백질 기반 나노 컴퓨터 개발

    회로로 기능하는 최초의 단백질 기반 나노 컴퓨팅 에이전트가 만들어졌다. 이는 당뇨병, 암과 같은 질병을 치료하기 위한 차세대 세포 기반 치료법 개발에 활용 가능하다. 암세포를 파괴하거나 손상 후 조직 재생을 촉진하는 것과 같은 세포 기반 요법을 위한 전통적인 합성 생물학 접근법은 세포 내에서 원하는 작용을 생성하는 단백질의 발현 또는 억제에 의존한다. 이 접근법은 시간이 걸리고(단백질이 발현되고…

  • | | | | | |

    24.2조원 과학기술 R&D 전략적 투자 “혁신 DNA 실현”

    과학기술정보통신부, 2020년도 업무계획 발표 과학기술정보통신부는 16일 방송통신위원회와 합동으로 2020년도 업무계획을 과학기술·ICT 산실 대덕단지(ETRI)에서 발표했다. 과기정통부 업무보고는 “확실한 변화 대한민국 2020!”, “혁신의 DNA, 과학기술 강국”이라는 슬로건으로, 아무도 흔들 수 없는 기초가 튼튼한 과학기술 강국, DNA를 기반으로 혁신을 선도하는 AI일등 국가, 미래 성장을 견인하는 디지털 미디어 강국 이라는 3대 전략을 중점 추진, 혁신 성장 의지를 담았다. 2019년…

  • | | | | |

    지구의 물은 어디에서 왔을까?

    물은 지구 표면의 71%를 차지하지만, 이 엄청난 양의 물이 언제 어떻게 지구에 존재는지 아무도 모른다. 새로운 연구는 이 질문에 답하는 데 한 걸음 더 다가가도록 했다. 미국 메릴랜드 대학교(University of Maryland, UMD) 지질학과 조교수 메간 뉴콤(Megan Newcombe)이 이끄는 연구자들은 41억 2000만 년 전 태양계 형성 이후 우주에 떠다니던 녹은 운석(melted meteorites)을 분석했다. 그들은 이 운석의…

  • | | | |

    미래 컴퓨터, 인간 뇌 세포에서 작동

    인간의 뇌 세포로 구동되는 “바이오 컴퓨터(biocomputer)”는 현 세기 내에 개발될 수 있다. 미국 존스 홉킨스 대학(Johns Hopkins University) 연구팀은 오늘 Frontiers in Science 저널에 “오가노이드 지능”에 대한 계획을 요약했다. 이 작업을 주도하고 있는 존스 홉킨스대 교수 Thomas Hartung은 “컴퓨팅과 인공 지능은 기술 혁명을 주도해 왔지만 한계에 도달하고 있다”며 “바이오컴퓨팅은 계산 능력을 압축하고 효율성을 높여 현재의…

  • | | | |

    당뇨 치료제 효능 억제 장내미생물 대사체

    한국연구재단은 고아라 교수(성균관대 의대) 연구팀과 프레드릭 백헤드 교수(스웨덴 예테보리대) 연구팀이 장내미생물 대사체가 당뇨병 약인 메포민의 혈당조절 실패에 미치는 영향을 규명했다고 밝혔다. 모든 사람이 같은 약물에 대해 동일한 반응을 나타내지 않으므로 약물의 효능을 증대시키고 부작용을 줄이기 위해서는 약물에 대한 개인별 반응 차이를 유도하는 기작을 이해하는 것이 중요하다. 연구팀은 장내미생물 대사체인 이미다졸 프로피오네이트(아이엠피)가 당뇨병 약인 메포민의 작용을…

  • | | |

    인공지능 빅데이터 국제표준 2건 승인

    과학기술정보통신부 국립전파연구원은 ‘ISO/IEC JTC 1/SC 42’ 제4차 국제표준화회의(일본 도쿄, 10.7.~10.11.)에서 우리나라가 제안한 빅데이터 분야의 표준안이 국제표준으로 승인됐다고 밝혔다. ‘ISO/IEC JTC 1/SC 42 (인공지능) ‘는 국제표준화기구(ISO)와 국제전기기술위원회(IEC)가 정보기술 분야 국제표준화를 위해 운영 중인 합동기술위원회(JTC 1)의 인공지능 분과위원회다. 관련 분과위에서 이번에 승인된 표준은 빅데이터를 수집‧저장‧처리하는 단계별로 요구되는 공통 기능과 역할을 정의하고, 데이터 생산자와 서비스 제공자간에게 필요한 데이터…