본문

서브메뉴

Towards Reliable AI for Materials Discovery at Scale
Towards Reliable AI for Materials Discovery at Scale
Towards Reliable AI for Materials Discovery at Scale

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202104836
ISBN  
9798297600669
DDC  
542
저자명  
Deng, Bowen.
서명/저자  
Towards Reliable AI for Materials Discovery at Scale
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
151 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-04, Section: B.
주기사항  
Advisor: Ceder, Gerbrand.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약Artificial intelligence (AI) is increasingly shifting the paradigm of scientific discovery to accelerate research and solve real-world scientific challenges. While ab initio quantum mechanical simulation methods, such as density functional theory (DFT), offer the theoretical foundation to investigate material and chemical science problems at the atomic and electronic levels, their computational demands limit their applicability in both spatial and temporal scales. On the other hand, machine learning interatomic potentials (MLIPs) have enabled the opportunity to scale up quantum mechanical simulations to realistic scales by leveraging machine learning (ML) and neural networks (NNs) to learn and emulate atomic interactions. Recent advancements have led to foundation potentials (FPs) that are pre-trained on comprehensive materials datasets, providing opportunities for universal interatomic potential and foundation ML models.This thesis discusses the datasets, algorithms, benchmarks, and applications of MLIPs and FPs. We introduce the Crystal Hamiltonian Graph neural-Network (CHGNet), a graph neural network (GNN) based FP that learns and predicts the universal potential energy surface (PES) with the incorporation of atomic charge information. CHGNet is pre-trained on the Materials Project Trajectory (MPtrj) dataset, a comprehensive collection of over 1.5 million DFT calculations that spans the whole periodic table. We will demonstrate the application of CHGNet in modeling multiple energy-storage materials, including cathodes such as LixMnO2, LixMn0.8Ti0.1O1.9F0.1, LixFePO4, and solid electrolytes such as Li3La3Te2O12 and Li2ZrCl6. We highlight the insights and design principles that can be learned from the charge-informed large-scale simulations enabled by CHGNet.To further extend the simulation scale of MLIPs, we present DistMLIP, an efficient multi-GPU distributed inference platform for MLIP simulations. By partitioning the atomic graphs across multiple GPUs with DistMLIP, we show that current FPs can perform million-atom-scale simulations with a few GPUs.Benchmarking MLIP's accuracy is critical to ensure its modeling reliability. We discuss the rigorous benchmark study undertaken by Matbench Discovery to test FPs' ability to predict crystal stability through calculating bulk materials' energies. To further assess the FP's performance in out of distribution (OOD) PES regions, we present a series of benchmarks on materials modeling tasks such as surface and defect calculations. We found a consistent PES softening effect in all FPs and modeling tasks, characterized by energy and force under predictions. The PES softening issue behavior originates primarily from the systematically underpredicted PES curvature, which derives from the biased sampling of near-equilibrium atomic arrangements in FP pre-training datasets.We highlight the need for comprehensively sampled datasets to improve the reliability of FPs and avoid failure mechanisms such as the PES softening issue we identified. To address this concern, we will discuss the development of MatPES, a next-generation foundational materials dataset with improved PES sampling and high-fidelity DFT calculations. We will also discuss the open-sourced MLIP library, MatGL, that fosters straightforward adoption of material AIs. We hope these efforts discussed in this thesis present an enabling step towards reliable AI for materials discovery at scale and can continuously support advancements in materials and AI research.
일반주제명  
Computational chemistry
일반주제명  
Materials science
일반주제명  
Engineering
키워드  
Li-ion battery
키워드  
Machine learning
키워드  
Machine learning interatomic potentials
키워드  
Materials modeling
키워드  
Solid state electrolyte
기타저자  
University of California, Berkeley Materials Science & Engineering
기본자료저록  
Dissertations Abstracts International. 87-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359113
■00520260202104836
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798297600669
■035    ▼a(MiAaPQ)AAI32171584
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a542
■1001  ▼aDeng,  Bowen.
■24510▼aTowards  Reliable  AI  for  Materials  Discovery  at  Scale
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a151  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-04,  Section:  B.
■500    ▼aAdvisor:  Ceder,  Gerbrand.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aArtificial  intelligence  (AI)  is  increasingly  shifting  the  paradigm  of  scientific  discovery  to  accelerate  research  and  solve  real-world  scientific  challenges.  While  ab  initio  quantum  mechanical  simulation  methods,  such  as  density  functional  theory  (DFT),  offer  the  theoretical  foundation  to  investigate  material  and  chemical  science  problems  at  the  atomic  and  electronic  levels,  their  computational  demands  limit  their  applicability  in  both  spatial  and  temporal  scales.  On  the  other  hand,  machine  learning  interatomic  potentials  (MLIPs)  have  enabled  the  opportunity  to  scale  up  quantum  mechanical  simulations  to  realistic  scales  by  leveraging  machine  learning  (ML)  and  neural  networks  (NNs)  to  learn  and  emulate  atomic  interactions.  Recent  advancements  have  led  to  foundation  potentials  (FPs)  that  are  pre-trained  on  comprehensive  materials  datasets,  providing  opportunities  for  universal  interatomic  potential  and  foundation  ML  models.This  thesis  discusses  the  datasets,  algorithms,  benchmarks,  and  applications  of  MLIPs  and  FPs.  We  introduce  the  Crystal  Hamiltonian  Graph  neural-Network  (CHGNet),  a  graph  neural  network  (GNN)  based  FP  that  learns  and  predicts  the  universal  potential  energy  surface  (PES)  with  the  incorporation  of  atomic  charge  information.  CHGNet  is  pre-trained  on  the  Materials  Project  Trajectory  (MPtrj)  dataset,  a  comprehensive  collection  of  over  1.5  million  DFT  calculations  that  spans  the  whole  periodic  table.  We  will  demonstrate  the  application  of  CHGNet  in  modeling  multiple  energy-storage  materials,  including  cathodes  such  as  LixMnO2,  LixMn0.8Ti0.1O1.9F0.1,  LixFePO4,  and  solid  electrolytes  such  as  Li3La3Te2O12  and  Li2ZrCl6.  We  highlight  the  insights  and  design  principles  that  can  be  learned  from  the  charge-informed  large-scale  simulations  enabled  by  CHGNet.To  further  extend  the  simulation  scale  of  MLIPs,  we  present  DistMLIP,  an  efficient  multi-GPU  distributed  inference  platform  for  MLIP  simulations.  By  partitioning  the  atomic  graphs  across  multiple  GPUs  with  DistMLIP,  we  show  that  current  FPs  can  perform  million-atom-scale  simulations  with  a  few  GPUs.Benchmarking  MLIP's  accuracy  is  critical  to  ensure  its  modeling  reliability.  We  discuss  the  rigorous  benchmark  study  undertaken  by  Matbench  Discovery  to  test  FPs'  ability  to  predict  crystal  stability  through  calculating  bulk  materials'  energies.  To  further  assess  the  FP's  performance  in  out  of  distribution  (OOD)  PES  regions,  we  present  a  series  of  benchmarks  on  materials  modeling  tasks  such  as  surface  and  defect  calculations.  We  found  a  consistent  PES  softening  effect  in  all  FPs  and  modeling  tasks,  characterized  by  energy  and  force  under  predictions.  The  PES  softening  issue  behavior  originates  primarily  from  the  systematically  underpredicted  PES  curvature,  which  derives  from  the  biased  sampling  of  near-equilibrium  atomic  arrangements  in  FP  pre-training  datasets.We  highlight  the  need  for  comprehensively  sampled  datasets  to  improve  the  reliability  of  FPs  and  avoid  failure  mechanisms  such  as  the  PES  softening  issue  we  identified.  To  address  this  concern,  we  will  discuss  the  development  of  MatPES,  a  next-generation  foundational  materials  dataset  with  improved  PES  sampling  and  high-fidelity  DFT  calculations.  We  will  also  discuss  the  open-sourced  MLIP  library,  MatGL,  that  fosters  straightforward  adoption  of  material  AIs.  We  hope  these  efforts  discussed  in  this  thesis  present  an  enabling  step  towards  reliable  AI  for  materials  discovery  at  scale  and  can  continuously  support  advancements  in  materials  and  AI  research.
■590    ▼aSchool  code:  0028.
■650  4▼aComputational  chemistry
■650  4▼aMaterials  science
■650  4▼aEngineering
■653    ▼aLi-ion  battery
■653    ▼aMachine  learning
■653    ▼aMachine  learning  interatomic  potentials
■653    ▼aMaterials  modeling
■653    ▼aSolid  state  electrolyte
■690    ▼a0794
■690    ▼a0800
■690    ▼a0219
■690    ▼a0537
■71020▼aUniversity  of  California,  Berkeley▼bMaterials  Science  &  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g87-04B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359113▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF19201 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.