서브메뉴
검색
Accelerating Ai-Driven Scientific Discovery With End-To-End Learning and Random Projection
Accelerating Ai-Driven Scientific Discovery With End-To-End Learning and Random Projection
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211153108
- ISBN
- 9798346392620
- DDC
- 515.35
- 저자명
- Nasim, Md.
- 서명/저자
- Accelerating Ai-Driven Scientific Discovery With End-To-End Learning and Random Projection
- 발행사항
- [Sl] : Purdue University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 117 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
- 주기사항
- Advisor: Xue, Yexiang.
- 학위논문주기
- Thesis (Ph.D.)--Purdue University, 2024.
- 초록/해제
- 요약Scientific discovery of new knowledge from data can enhance our understanding of the physical world and lead to the innovation of new technologies. AI-driven methods can greatly accelerate scientific discovery and are essential for analyzing and identifying patterns in huge volumes of experimental data. However, current AI-driven scientific discovery pipeline suffers from several inefficiencies including but not limited to lack of precise modeling, lack of efficient learning methods, and lack of human-in-the-loop integrated frameworksin the scientific discovery loop. Such inefficiencies increase resource requirements such as expensive computing infrastructures, significant human expert efforts and subsequently slows down scientific discovery.In this thesis, I introduce a collection of methods to address the lack of precise modeling, lack of efficient learning methods and lack of human-in-the-loop integrated frameworks in AI-driven scientific discovery workflow. These methods include automatic physics model learning from partially annotated noisy video data, accelerated partial differential equation (PDE) physics model learning, and an integrated AI-driven platform for rapid analysis of experimental video data. My research has led to the discovery of a new size fluctuation property of material defectsexposed to high temperature and high irradiation environments such as inside nuclear reactors. Such discovery is essential for designing strong materials that are critical for energy applications.To address the lack of precise modeling of physics learning tasks, I developed NeuraDiff [1], an end-to-end method for learning phase field physics models from noisy video data. In previous learning approaches involving multiple disjoint steps, errors in one step can propagate to another, thus affecting the accuracy of the learned physics models. Trial-and-error simulation methods for learning physics model parameters are inefficient, heavily dependent on expert intuition and may not yield reasonably accurate physics models even after many trial iterations. By encoding the physics model equations directly into learning, end-to-end NeuraDiff framework can provide ≈ 100% accurate tracking of material defects and yield correct physics model parameters.
- 일반주제명
- Deep learning
- 일반주제명
- Defects
- 일반주제명
- Back propagation
- 일반주제명
- Fourier transforms
- 일반주제명
- Grain growth
- 일반주제명
- High temperature
- 일반주제명
- Neural networks
- 일반주제명
- Microscopy
- 일반주제명
- Heat
- 일반주제명
- Crowdsourcing
- 일반주제명
- Human error
- 일반주제명
- Radiation
- 일반주제명
- Data compression
- 일반주제명
- Computer science
- 일반주제명
- High temperature physics
- 일반주제명
- Mathematics
- 일반주제명
- Thermodynamics
- 기타저자
- Purdue University.
- 기본자료저록
- Dissertations Abstracts International. 86-05B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017164966
■00520250211153108
■006m o d
■007cr#unu||||||||
■020 ▼a9798346392620
■035 ▼a(MiAaPQ)AAI31682051
■035 ▼a(MiAaPQ)Purdue26815507
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a515.35
■1001 ▼aNasim, Md.
■24510▼aAccelerating Ai-Driven Scientific Discovery With End-To-End Learning and Random Projection
■260 ▼a[Sl]▼bPurdue University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a117 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-05, Section: B.
■500 ▼aAdvisor: Xue, Yexiang.
■5021 ▼aThesis (Ph.D.)--Purdue University, 2024.
■520 ▼aScientific discovery of new knowledge from data can enhance our understanding of the physical world and lead to the innovation of new technologies. AI-driven methods can greatly accelerate scientific discovery and are essential for analyzing and identifying patterns in huge volumes of experimental data. However, current AI-driven scientific discovery pipeline suffers from several inefficiencies including but not limited to lack of precise modeling, lack of efficient learning methods, and lack of human-in-the-loop integrated frameworksin the scientific discovery loop. Such inefficiencies increase resource requirements such as expensive computing infrastructures, significant human expert efforts and subsequently slows down scientific discovery.In this thesis, I introduce a collection of methods to address the lack of precise modeling, lack of efficient learning methods and lack of human-in-the-loop integrated frameworks in AI-driven scientific discovery workflow. These methods include automatic physics model learning from partially annotated noisy video data, accelerated partial differential equation (PDE) physics model learning, and an integrated AI-driven platform for rapid analysis of experimental video data. My research has led to the discovery of a new size fluctuation property of material defectsexposed to high temperature and high irradiation environments such as inside nuclear reactors. Such discovery is essential for designing strong materials that are critical for energy applications.To address the lack of precise modeling of physics learning tasks, I developed NeuraDiff [1], an end-to-end method for learning phase field physics models from noisy video data. In previous learning approaches involving multiple disjoint steps, errors in one step can propagate to another, thus affecting the accuracy of the learned physics models. Trial-and-error simulation methods for learning physics model parameters are inefficient, heavily dependent on expert intuition and may not yield reasonably accurate physics models even after many trial iterations. By encoding the physics model equations directly into learning, end-to-end NeuraDiff framework can provide ≈ 100% accurate tracking of material defects and yield correct physics model parameters.
■590 ▼aSchool code: 0183.
■650 4▼aPartial differential equations
■650 4▼aDeep learning
■650 4▼aDefects
■650 4▼aBack propagation
■650 4▼aFourier transforms
■650 4▼aGrain growth
■650 4▼aHigh temperature
■650 4▼aNeural networks
■650 4▼aMicroscopy
■650 4▼aHeat
■650 4▼aCrowdsourcing
■650 4▼aHuman error
■650 4▼aRadiation
■650 4▼aData compression
■650 4▼aComputer science
■650 4▼aHigh temperature physics
■650 4▼aMathematics
■650 4▼aThermodynamics
■690 ▼a0800
■690 ▼a0984
■690 ▼a0597
■690 ▼a0405
■690 ▼a0348
■71020▼aPurdue University.
■7730 ▼tDissertations Abstracts International▼g86-05B.
■790 ▼a0183
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164966▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


