Article Dans Une Revue Automation in Construction Année : 2025

Multi-LOD generative approach for multi-objective sustainability optimization from the early stages of building design

Résumé

Given the urgency of reducing the buildings' environmental impact, this article focuses on optimizing sustainability from the earliest design phases, when decisions have the greatest influence. To address the challenges posed by the coarse granularity of digital models during the sketching phase and the often-conflicting nature of sustainability criteria, a generative workflow is proposed. This workflow, based on a multi-Level of Detail (LOD) framework, enables the evaluation and tracking of multiple sustainability criteria throughout the design iterations. This systemic methodology integrates automated functional spatial-planning, hierarchical segmentation of construction solutions, and systematic exploration of Pareto-optimal alternatives for bi-objective optimization. The framework is validated during the sketch phase using life-cycle cost and global warming potential, across eight real-world office-building case studies. Feedback from ten construction experts confirms the Proof-of-Concept's effectiveness in supporting both retrospective and prospective decision-making, underscoring its potential to advance sustainable design practices in the Architecture, Engineering, and Construction sector.

Fichier principal
Vignette du fichier
Bouillon_Multi-LODgenerativeapproachinbuilding.pdf (6.71 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-05125651 , version 1 (23-06-2025)

Licence

Identifiants

Citer

Catherine Bouillon, Benjamin Cohen Boulakia, Karim Beddiar, Yves Jaboin, Fabrice Duval. Multi-LOD generative approach for multi-objective sustainability optimization from the early stages of building design. Automation in Construction, 2025, 177, pp.106326. ⟨10.1016/j.autcon.2025.106326⟩. ⟨hal-05125651⟩
672 Consultations
385 Téléchargements

Altmetric

Partager

  • More