Exploring machine learning-based archetypes for urban life cycle modeling (UBiM)

Urban analyses demand simplifications that balance modelling level of detail and scope broadness. Thus, classification by archetypes is a promising methodological approach. Such an approach is common for energy studies but rarely applied for Life Cycle Assessment (LCA) purposes. When archetypes are...

Full description

Saved in:
Bibliographic Details
Main Authors: Giseli Mary Colleto, Vanessa Gomes
Format: Article
Language:English
Published: Czech Technical University in Prague 2022-12-01
Series:Acta Polytechnica CTU Proceedings
Subjects:
Online Access:https://ojs.cvut.cz/ojs/index.php/APP/article/view/8295
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850111485742678016
author Giseli Mary Colleto
Vanessa Gomes
author_facet Giseli Mary Colleto
Vanessa Gomes
author_sort Giseli Mary Colleto
collection DOAJ
description Urban analyses demand simplifications that balance modelling level of detail and scope broadness. Thus, classification by archetypes is a promising methodological approach. Such an approach is common for energy studies but rarely applied for Life Cycle Assessment (LCA) purposes. When archetypes are used in urban LCA, they generally result from previous studies for classification and characterization according to parameters that directly affect the operational energy performance of buildings. This paper tackles two research questions: i) Is it appropriate to aggregate building stocks based on operational energy (OE) variables when life cycle impacts are investigated? ii) When integrated LCA (OE + embodied impacts) is pursued, would variables describing both interests simultaneously result in better representation than using operational energy-based clustering to predict embodied impacts and vice versa? Thus, we aim to confirm that, combining variables that govern OE and embodied impacts offers a better result than using OE to predict materials groupings, even if some adherence is lost relatively to single-objective clustering. Clustering experiments were carried out for the campus of the University of Campinas, Brazil. After unsupervised k-medoid (PAM) grouping, the data were submitted to a supervised learning (neural networks) classification method. Generated confusion matrices demonstrate how adherent the clustering is when considering one interest to predict the other in three situations. Results indicate that an operational energy-driven archetype fails to represent buildings from the embodied impacts viewpoint, and that merging operational energy and embodied impact variables would better support integrated life cycle impact predictions.
format Article
id doaj-art-32a2849422ef440f81c7ffef4428f47f
institution OA Journals
issn 2336-5382
language English
publishDate 2022-12-01
publisher Czech Technical University in Prague
record_format Article
series Acta Polytechnica CTU Proceedings
spelling doaj-art-32a2849422ef440f81c7ffef4428f47f2025-08-20T02:37:36ZengCzech Technical University in PragueActa Polytechnica CTU Proceedings2336-53822022-12-013816917510.14311/APP.2022.38.01695535Exploring machine learning-based archetypes for urban life cycle modeling (UBiM)Giseli Mary Colleto0Vanessa Gomes1University of Campinas, School of Civil Engineering and Architecture and Urbanism, Rua Saturnino de Brito, n° 224, Cidade Universitária Zeferino Vaz. CEP: 13083-889 – Campinas – São Paulo, BrazilUniversity of Campinas, School of Civil Engineering and Architecture and Urbanism, Rua Saturnino de Brito, n° 224, Cidade Universitária Zeferino Vaz. CEP: 13083-889 – Campinas – São Paulo, BrazilUrban analyses demand simplifications that balance modelling level of detail and scope broadness. Thus, classification by archetypes is a promising methodological approach. Such an approach is common for energy studies but rarely applied for Life Cycle Assessment (LCA) purposes. When archetypes are used in urban LCA, they generally result from previous studies for classification and characterization according to parameters that directly affect the operational energy performance of buildings. This paper tackles two research questions: i) Is it appropriate to aggregate building stocks based on operational energy (OE) variables when life cycle impacts are investigated? ii) When integrated LCA (OE + embodied impacts) is pursued, would variables describing both interests simultaneously result in better representation than using operational energy-based clustering to predict embodied impacts and vice versa? Thus, we aim to confirm that, combining variables that govern OE and embodied impacts offers a better result than using OE to predict materials groupings, even if some adherence is lost relatively to single-objective clustering. Clustering experiments were carried out for the campus of the University of Campinas, Brazil. After unsupervised k-medoid (PAM) grouping, the data were submitted to a supervised learning (neural networks) classification method. Generated confusion matrices demonstrate how adherent the clustering is when considering one interest to predict the other in three situations. Results indicate that an operational energy-driven archetype fails to represent buildings from the embodied impacts viewpoint, and that merging operational energy and embodied impact variables would better support integrated life cycle impact predictions.https://ojs.cvut.cz/ojs/index.php/APP/article/view/8295archetypesbuilding stock aggregationclusteringlcalife cycle impactsurban modelling
spellingShingle Giseli Mary Colleto
Vanessa Gomes
Exploring machine learning-based archetypes for urban life cycle modeling (UBiM)
Acta Polytechnica CTU Proceedings
archetypes
building stock aggregation
clustering
lca
life cycle impacts
urban modelling
title Exploring machine learning-based archetypes for urban life cycle modeling (UBiM)
title_full Exploring machine learning-based archetypes for urban life cycle modeling (UBiM)
title_fullStr Exploring machine learning-based archetypes for urban life cycle modeling (UBiM)
title_full_unstemmed Exploring machine learning-based archetypes for urban life cycle modeling (UBiM)
title_short Exploring machine learning-based archetypes for urban life cycle modeling (UBiM)
title_sort exploring machine learning based archetypes for urban life cycle modeling ubim
topic archetypes
building stock aggregation
clustering
lca
life cycle impacts
urban modelling
url https://ojs.cvut.cz/ojs/index.php/APP/article/view/8295
work_keys_str_mv AT giselimarycolleto exploringmachinelearningbasedarchetypesforurbanlifecyclemodelingubim
AT vanessagomes exploringmachinelearningbasedarchetypesforurbanlifecyclemodelingubim