서브메뉴
검색
From Morphogenesis to Synergetic Resilience: Artificial Intelligence-Powered Urban Neighborhood Energy Transition
From Morphogenesis to Synergetic Resilience: Artificial Intelligence-Powered Urban Neighborhood Energy Transition
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202104710
- ISBN
- 9798297600959
- DDC
- 307
- 저자명
- Zhuang, Xinwei.
- 서명/저자
- From Morphogenesis to Synergetic Resilience: Artificial Intelligence-Powered Urban Neighborhood Energy Transition
- 발행사항
- [Sl] : University of California, Berkeley, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 235 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-04, Section: B.
- 주기사항
- Advisor: Caldas, Luisa.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Berkeley, 2025.
- 초록/해제
- 요약This dissertation unfolds at the intersection of generative design, artificial intelligence, and urban energy planning. It proposes a computational framework to support urban neighborhoods evolve toward more adaptive and resilient forms, synthesizing morphology, energy systems, and contextual intelligence. The framework integrates generative modeling, representation learning, and constrained optimization to enhance urban energy resilience. The research positions the neighborhood as a critical scale for aligning design and energy infrastructure, where spatial morphology, energy performance, and system dynamics converge.The work unfolds through three modules: Genesis, which generates building arrangements responsive to context and form-based constraints using generative artificial intelligence; Synthesis, which employs representation learning to encode spatial-energy relationships among buildings and abstract recurring typologies; and Synergic Resilience, which optimizes distributed energy resources partitions and promotes energy-sharing at the neighborhood scale. The framework is demonstrated using real-world data. Each module is tested in a major U.S. city: Morphogenesis in New York City, Morphosynthesis in Los Angeles, and Morphodynamics in San Francisco, revealing opportunities for AI-powered design and energy interventions across different urban morphologies.This dissertation bridges the gap between architectural morphology and energy performance in pursuit of enhanced neighborhood energy resilience. The findings suggest that collective energy strategies, emergent from morphology abstraction and AI-supported coordination, can catalyze urban forms that are more adaptable, just, and resilient. The dissertation repositions neighborhoods as the stage for architectural intelligence to materialize across form and energy, contributing to emerging discourses that resilience emerges in situ, shaped by context, constraint, and collective adaptation.
- 일반주제명
- Urban planning
- 키워드
- Urban morphology
- 기타저자
- University of California, Berkeley Architecture
- 기본자료저록
- Dissertations Abstracts International. 87-04B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017358497
■00520260202104710
■006m o d
■007cr#unu||||||||
■020 ▼a9798297600959
■035 ▼a(MiAaPQ)AAI32118267
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a307
■1001 ▼aZhuang, Xinwei.
■24510▼aFrom Morphogenesis to Synergetic Resilience: Artificial Intelligence-Powered Urban Neighborhood Energy Transition
■260 ▼a[Sl]▼bUniversity of California, Berkeley▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a235 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-04, Section: B.
■500 ▼aAdvisor: Caldas, Luisa.
■5021 ▼aThesis (Ph.D.)--University of California, Berkeley, 2025.
■520 ▼aThis dissertation unfolds at the intersection of generative design, artificial intelligence, and urban energy planning. It proposes a computational framework to support urban neighborhoods evolve toward more adaptive and resilient forms, synthesizing morphology, energy systems, and contextual intelligence. The framework integrates generative modeling, representation learning, and constrained optimization to enhance urban energy resilience. The research positions the neighborhood as a critical scale for aligning design and energy infrastructure, where spatial morphology, energy performance, and system dynamics converge.The work unfolds through three modules: Genesis, which generates building arrangements responsive to context and form-based constraints using generative artificial intelligence; Synthesis, which employs representation learning to encode spatial-energy relationships among buildings and abstract recurring typologies; and Synergic Resilience, which optimizes distributed energy resources partitions and promotes energy-sharing at the neighborhood scale. The framework is demonstrated using real-world data. Each module is tested in a major U.S. city: Morphogenesis in New York City, Morphosynthesis in Los Angeles, and Morphodynamics in San Francisco, revealing opportunities for AI-powered design and energy interventions across different urban morphologies.This dissertation bridges the gap between architectural morphology and energy performance in pursuit of enhanced neighborhood energy resilience. The findings suggest that collective energy strategies, emergent from morphology abstraction and AI-supported coordination, can catalyze urban forms that are more adaptable, just, and resilient. The dissertation repositions neighborhoods as the stage for architectural intelligence to materialize across form and energy, contributing to emerging discourses that resilience emerges in situ, shaped by context, constraint, and collective adaptation.
■590 ▼aSchool code: 0028.
■650 4▼aUrban planning
■653 ▼aBuilding archetype
■653 ▼aEnergy resilience
■653 ▼aGenerative design
■653 ▼aRepresentation learning
■653 ▼aUrban morphology
■690 ▼a0729
■690 ▼a0800
■690 ▼a0543
■690 ▼a0999
■71020▼aUniversity of California, Berkeley▼bArchitecture.
■7730 ▼tDissertations Abstracts International▼g87-04B.
■790 ▼a0028
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358497▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
