Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Predicting the presence of hazardous materials in buildings using machine learning
RISE Research Institutes of Sweden, Säkerhet och transport, Mätteknik. Lund University, Sweden.ORCID-id: 0000-0002-2178-5391
RISE Research Institutes of Sweden, Säkerhet och transport, Mätteknik.ORCID-id: 0000-0002-9860-4472
RISE Research Institutes of Sweden, Samhällsbyggnad. Lund University, Sweden.ORCID-id: 0000-0002-3863-0740
RISE Research Institutes of Sweden, Samhällsbyggnad, Systemomställning och tjänsteinnovation.ORCID-id: 0000-0002-5044-6989
Visa övriga samt affilieringar
2022 (Engelska)Ingår i: Building and Environment, ISSN 0360-1323, E-ISSN 1873-684X, Vol. 213, artikel-id 108894Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Identifying in situ hazardous materials can improve demolition waste recyclability and reduce project uncertainties concerning cost overrun and delay. With the attempt to characterize their detection patterns in buildings, the study investigates the prediction potential of machine learning techniques with hazardous waste inventories and building registers as input data. By matching, validating, and assuring the quality of empirical data, a hazardous material dataset for training, testing, and validation was created. The objectives of the explorative study are to highlight the challenges in machine learning pipeline development and verify two prediction hypotheses. Our findings show an average of 74% and 83% accuracy rates in predicting asbestos pipe insulation in multifamily houses and PCB joints or sealants in school buildings in two major Swedish cities Gothenburg and Stockholm. Similarly, 78% and 83% of recall rates were obtained for imbalanced classification. By correlating the training sample size and cross-validation accuracy, the bias and variance issues were assessed in learning curves. In general, the models perform well on the limited dataset, yet collecting more training data can improve the model's generalizability to other building stocks, meanwhile decreasing the chance of overfitting. Furthermore, the average impact on the model output magnitude of each feature was illustrated. The proposed applied machine learning approach is promising for in situ hazardous material management and could support decision-making regarding risk evaluation in selective demolition work. © 2022 The Author(s)

Ort, förlag, år, upplaga, sidor
Elsevier Ltd , 2022. Vol. 213, artikel-id 108894
Nyckelord [en]
Asbestos, Circular economy, Hazardous materials, Machine learning, PCB, Pre-demolition audit, Decision making, Demolition, Forecasting, Hazards, Organic pollutants, Cost-overruns, Demolition wastes, Hazardous wastes, In-buildings, Input datas, Machine learning techniques, Project uncertainty, Recyclability, Polychlorinated biphenyls
Nationell ämneskategori
Husbyggnad
Identifikatorer
URN: urn:nbn:se:ri:diva-58771DOI: 10.1016/j.buildenv.2022.108894Scopus ID: 2-s2.0-85124704384OAI: oai:DiVA.org:ri-58771DiVA, id: diva2:1642226
Anmärkning

Funding details: Stiftelsen för Strategisk Forskning, SSF, FID18-0021; Funding text 1: This research was funded by the Swedish Foundation for Strategic Research (SSF) , grant number FID18-0021 .

Tillgänglig från: 2022-03-04 Skapad: 2022-03-04 Senast uppdaterad: 2024-02-14Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Wu, Pei-YuSandels, ClaesMjörnell, KristinaMangold, MikaelJohansson, Tim

Sök vidare i DiVA

Av författaren/redaktören
Wu, Pei-YuSandels, ClaesMjörnell, KristinaMangold, MikaelJohansson, Tim
Av organisationen
MätteknikSamhällsbyggnadSystemomställning och tjänsteinnovation
I samma tidskrift
Building and Environment
Husbyggnad

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 101 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf