Loading [MathJax]/extensions/tex2jax.js

Introducing causal inference in the energy-efficient building design process

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autorschaft

  • Xia Chen
  • Jimmy Abualdenien
  • Manav Mahan Singh
  • André Borrmann
  • Philipp Geyer

Externe Organisationen

  • Technische Universität Berlin
  • Technische Universität München (TUM)

Details

OriginalspracheEnglisch
Aufsatznummer112583
Seitenumfang14
FachzeitschriftEnergy and Buildings
Jahrgang277
Frühes Online-Datum22 Okt. 2022
PublikationsstatusVeröffentlicht - 15 Dez. 2022

Abstract

“What-if” questions are intuitively generated and commonly asked during the design process. Engineers and architects need to inherently conduct design decisions, progressing from one phase to another. They either use empirical domain experience, simulations, or data-driven methods to acquire consequential feedback. We take an example from an interdisciplinary domain of energy-efficient building design to argue that the current methods for decision support have limitations or deficiencies in four aspects: parametric independency identification, gaps in integrating knowledge-based and data-driven approaches, less explicit model interpretation, and ambiguous decision support boundaries. In this study, we first clarify the nature of dynamic experience in individuals and constant principal knowledge in design. Subsequently, we introduce causal inference into the domain. A four-step process is proposed to discover and analyze parametric dependencies in a mathematically rigorous and computationally efficient manner by identifying the causal diagram with interventions. The causal diagram provides a nexus for integrating domain knowledge with data-driven methods, providing interpretability and testability against the domain experience within the design space. Extracting causal structures from the data is close to the nature design reasoning process. As an illustration, we applied the properties of the proposed estimators through simulations. The paper concludes with a feasibility study demonstrating the proposed framework's realization.

ASJC Scopus Sachgebiete

Zitieren

Introducing causal inference in the energy-efficient building design process. / Chen, Xia; Abualdenien, Jimmy; Mahan Singh, Manav et al.
in: Energy and Buildings, Jahrgang 277, 112583, 15.12.2022.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Chen X, Abualdenien J, Mahan Singh M, Borrmann A, Geyer P. Introducing causal inference in the energy-efficient building design process. Energy and Buildings. 2022 Dez 15;277:112583. Epub 2022 Okt 22. doi: 10.48550/arXiv.2203.10115, 10.1016/j.enbuild.2022.112583
Chen, Xia ; Abualdenien, Jimmy ; Mahan Singh, Manav et al. / Introducing causal inference in the energy-efficient building design process. in: Energy and Buildings. 2022 ; Jahrgang 277.
Download
@article{43c7f7b8e2a64f2fa575ecfd0de6c8ec,
title = "Introducing causal inference in the energy-efficient building design process",
abstract = "“What-if” questions are intuitively generated and commonly asked during the design process. Engineers and architects need to inherently conduct design decisions, progressing from one phase to another. They either use empirical domain experience, simulations, or data-driven methods to acquire consequential feedback. We take an example from an interdisciplinary domain of energy-efficient building design to argue that the current methods for decision support have limitations or deficiencies in four aspects: parametric independency identification, gaps in integrating knowledge-based and data-driven approaches, less explicit model interpretation, and ambiguous decision support boundaries. In this study, we first clarify the nature of dynamic experience in individuals and constant principal knowledge in design. Subsequently, we introduce causal inference into the domain. A four-step process is proposed to discover and analyze parametric dependencies in a mathematically rigorous and computationally efficient manner by identifying the causal diagram with interventions. The causal diagram provides a nexus for integrating domain knowledge with data-driven methods, providing interpretability and testability against the domain experience within the design space. Extracting causal structures from the data is close to the nature design reasoning process. As an illustration, we applied the properties of the proposed estimators through simulations. The paper concludes with a feasibility study demonstrating the proposed framework's realization.",
author = "Xia Chen and Jimmy Abualdenien and {Mahan Singh}, Manav and Andr{\'e} Borrmann and Philipp Geyer",
note = "Funding Information: We gratefully acknowledge the German Research Foundation (DFG) support for funding the project under grant GE 1652/3-2 in the Researcher Unit FOR 2363. ",
year = "2022",
month = dec,
day = "15",
doi = "10.48550/arXiv.2203.10115",
language = "English",
volume = "277",
journal = "Energy and Buildings",
issn = "0378-7788",
publisher = "Elsevier BV",

}

Download

TY - JOUR

T1 - Introducing causal inference in the energy-efficient building design process

AU - Chen, Xia

AU - Abualdenien, Jimmy

AU - Mahan Singh, Manav

AU - Borrmann, André

AU - Geyer, Philipp

N1 - Funding Information: We gratefully acknowledge the German Research Foundation (DFG) support for funding the project under grant GE 1652/3-2 in the Researcher Unit FOR 2363.

PY - 2022/12/15

Y1 - 2022/12/15

N2 - “What-if” questions are intuitively generated and commonly asked during the design process. Engineers and architects need to inherently conduct design decisions, progressing from one phase to another. They either use empirical domain experience, simulations, or data-driven methods to acquire consequential feedback. We take an example from an interdisciplinary domain of energy-efficient building design to argue that the current methods for decision support have limitations or deficiencies in four aspects: parametric independency identification, gaps in integrating knowledge-based and data-driven approaches, less explicit model interpretation, and ambiguous decision support boundaries. In this study, we first clarify the nature of dynamic experience in individuals and constant principal knowledge in design. Subsequently, we introduce causal inference into the domain. A four-step process is proposed to discover and analyze parametric dependencies in a mathematically rigorous and computationally efficient manner by identifying the causal diagram with interventions. The causal diagram provides a nexus for integrating domain knowledge with data-driven methods, providing interpretability and testability against the domain experience within the design space. Extracting causal structures from the data is close to the nature design reasoning process. As an illustration, we applied the properties of the proposed estimators through simulations. The paper concludes with a feasibility study demonstrating the proposed framework's realization.

AB - “What-if” questions are intuitively generated and commonly asked during the design process. Engineers and architects need to inherently conduct design decisions, progressing from one phase to another. They either use empirical domain experience, simulations, or data-driven methods to acquire consequential feedback. We take an example from an interdisciplinary domain of energy-efficient building design to argue that the current methods for decision support have limitations or deficiencies in four aspects: parametric independency identification, gaps in integrating knowledge-based and data-driven approaches, less explicit model interpretation, and ambiguous decision support boundaries. In this study, we first clarify the nature of dynamic experience in individuals and constant principal knowledge in design. Subsequently, we introduce causal inference into the domain. A four-step process is proposed to discover and analyze parametric dependencies in a mathematically rigorous and computationally efficient manner by identifying the causal diagram with interventions. The causal diagram provides a nexus for integrating domain knowledge with data-driven methods, providing interpretability and testability against the domain experience within the design space. Extracting causal structures from the data is close to the nature design reasoning process. As an illustration, we applied the properties of the proposed estimators through simulations. The paper concludes with a feasibility study demonstrating the proposed framework's realization.

UR - http://www.scopus.com/inward/record.url?scp=85140805424&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2203.10115

DO - 10.48550/arXiv.2203.10115

M3 - Article

AN - SCOPUS:85140805424

VL - 277

JO - Energy and Buildings

JF - Energy and Buildings

SN - 0378-7788

M1 - 112583

ER -