Comparison of regression models for estimation of carbon emissions during building's lifecycle using designing factors: a case study of residential buildings in Tianjin, China
•Based on the life cycle assessment theory, this paper has estimated and analyzed carbon emissions of 207 residential buildings in Tianjin.•Correlation analysis and elastic net were jointly used to select 12 design factors as independent variables for predictive models.•Four frequently-used regressi...
Gespeichert in:
Veröffentlicht in: | Energy and buildings 2019-12, Vol.204, p.109519, Article 109519 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | 109519 |
container_title | Energy and buildings |
container_volume | 204 |
creator | Xikai, Mao Lixiong, Wang Jiwei, Li Xiaoli, Quan Tongyao, Wu |
description | •Based on the life cycle assessment theory, this paper has estimated and analyzed carbon emissions of 207 residential buildings in Tianjin.•Correlation analysis and elastic net were jointly used to select 12 design factors as independent variables for predictive models.•Four frequently-used regression techniques, PCR, RF, MLP and SVR, were used to develop regression models of carbon emissions.
Many studies have been conducted on life cycle assessment and control measures for carbon emissions of buildings. Methods proposed by these studies usually require not only specific accounting model, but also detailed inventory data, which is not available at early design stage. Seeing that the importance of design phase to carbon emissions during building's lifecycle, a study on regression model of carbon emissions using designing factors was done. Firstly, based on process analysis method, the carbon emissions of 207 residential buildings in Tianjin were calculated. The results show that annual carbon emissions per floor area are between 30 and 60 kgCO2/(m2•year), with manufacture phase and operation phase accounting for 11%–25% and 75%–87%, respectively. Then, correlation analysis and elastic net were used to determine 12 designing factors for predictive model; At last, four regression techniques, PCR, RF, MLP and SVR were used to develop regression models, respectively; comparison and process analysis of model development were given later. The results show that SVR has the optimal predictive accuracy among four models, its corresponding coefficient of determination can reach to 0.800. This regression model can be utilized to estimate carbon emissions based on designing factors, which can help designers make a strategic decision at early stage. |
doi_str_mv | 10.1016/j.enbuild.2019.109519 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2319718636</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0378778819313672</els_id><sourcerecordid>2319718636</sourcerecordid><originalsourceid>FETCH-LOGICAL-c400t-5dd0178687ab664ff65b68f9c139e0a25cbbc9cbf14257e835ad7adec05a0c303</originalsourceid><addsrcrecordid>eNqFUU1v1DAQtSoqsbT8BCRLHLiQxU42dsIFoRVfUiUu5Ww59ng7UdZePAnS_qr-RbxNxZWTnz1v3njeY-yNFFsppPowbiEOC05-WwvZl7e-lf0V28hO15WSunvBNqLRXaV1171kr4hGIYRqtdywx306nmxGSpGnwDMcMhBhuR2Th4l4SJkDzXi0M64cZ_NQEBzxiUjcLxnjgT99oYB3xCcM4M5uAr7QpeSB8BAvKFg3p0wfuS06BJzmxZ_XyYQe4ox2-qdEHCO_RxtHjO_5_gGjvWXXwU4Er5_PG_br65f7_ffq7ue3H_vPd5XbCTFXrfeiLK46bQeldiGodlBd6J1sehC2bt0wuN4NQe7qVkPXtNZr68GJ1grXiOaGvV11Tzn9XooBZkxLjmWkqRvZa9mpRhVWu7JcTkQZgjnl4lQ-GynMJRszmudszCUbs2ZT-j6tfcVh-IOQDTmE6MBjBjcbn_A_Cn8B7zufLQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2319718636</pqid></control><display><type>article</type><title>Comparison of regression models for estimation of carbon emissions during building's lifecycle using designing factors: a case study of residential buildings in Tianjin, China</title><source>Elsevier ScienceDirect Journals Complete</source><creator>Xikai, Mao ; Lixiong, Wang ; Jiwei, Li ; Xiaoli, Quan ; Tongyao, Wu</creator><creatorcontrib>Xikai, Mao ; Lixiong, Wang ; Jiwei, Li ; Xiaoli, Quan ; Tongyao, Wu</creatorcontrib><description>•Based on the life cycle assessment theory, this paper has estimated and analyzed carbon emissions of 207 residential buildings in Tianjin.•Correlation analysis and elastic net were jointly used to select 12 design factors as independent variables for predictive models.•Four frequently-used regression techniques, PCR, RF, MLP and SVR, were used to develop regression models of carbon emissions.
Many studies have been conducted on life cycle assessment and control measures for carbon emissions of buildings. Methods proposed by these studies usually require not only specific accounting model, but also detailed inventory data, which is not available at early design stage. Seeing that the importance of design phase to carbon emissions during building's lifecycle, a study on regression model of carbon emissions using designing factors was done. Firstly, based on process analysis method, the carbon emissions of 207 residential buildings in Tianjin were calculated. The results show that annual carbon emissions per floor area are between 30 and 60 kgCO2/(m2•year), with manufacture phase and operation phase accounting for 11%–25% and 75%–87%, respectively. Then, correlation analysis and elastic net were used to determine 12 designing factors for predictive model; At last, four regression techniques, PCR, RF, MLP and SVR were used to develop regression models, respectively; comparison and process analysis of model development were given later. The results show that SVR has the optimal predictive accuracy among four models, its corresponding coefficient of determination can reach to 0.800. This regression model can be utilized to estimate carbon emissions based on designing factors, which can help designers make a strategic decision at early stage.</description><identifier>ISSN: 0378-7788</identifier><identifier>EISSN: 1872-6178</identifier><identifier>DOI: 10.1016/j.enbuild.2019.109519</identifier><language>eng</language><publisher>Lausanne: Elsevier B.V</publisher><subject>Building lifecycle ; Buildings ; Carbon ; Carbon emissions ; Correlation analysis ; Decision making ; Design ; Elastic analysis ; Emission measurements ; Life cycle analysis ; Life cycle assessment ; Life cycles ; Mathematical analysis ; Model accuracy ; Prediction models ; Predictive model ; Regression analysis ; Regression models ; Residential areas ; Residential building ; Residential buildings</subject><ispartof>Energy and buildings, 2019-12, Vol.204, p.109519, Article 109519</ispartof><rights>2019</rights><rights>Copyright Elsevier BV Dec 1, 2019</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c400t-5dd0178687ab664ff65b68f9c139e0a25cbbc9cbf14257e835ad7adec05a0c303</citedby><cites>FETCH-LOGICAL-c400t-5dd0178687ab664ff65b68f9c139e0a25cbbc9cbf14257e835ad7adec05a0c303</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0378778819313672$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3537,27901,27902,65534</link.rule.ids></links><search><creatorcontrib>Xikai, Mao</creatorcontrib><creatorcontrib>Lixiong, Wang</creatorcontrib><creatorcontrib>Jiwei, Li</creatorcontrib><creatorcontrib>Xiaoli, Quan</creatorcontrib><creatorcontrib>Tongyao, Wu</creatorcontrib><title>Comparison of regression models for estimation of carbon emissions during building's lifecycle using designing factors: a case study of residential buildings in Tianjin, China</title><title>Energy and buildings</title><description>•Based on the life cycle assessment theory, this paper has estimated and analyzed carbon emissions of 207 residential buildings in Tianjin.•Correlation analysis and elastic net were jointly used to select 12 design factors as independent variables for predictive models.•Four frequently-used regression techniques, PCR, RF, MLP and SVR, were used to develop regression models of carbon emissions.
Many studies have been conducted on life cycle assessment and control measures for carbon emissions of buildings. Methods proposed by these studies usually require not only specific accounting model, but also detailed inventory data, which is not available at early design stage. Seeing that the importance of design phase to carbon emissions during building's lifecycle, a study on regression model of carbon emissions using designing factors was done. Firstly, based on process analysis method, the carbon emissions of 207 residential buildings in Tianjin were calculated. The results show that annual carbon emissions per floor area are between 30 and 60 kgCO2/(m2•year), with manufacture phase and operation phase accounting for 11%–25% and 75%–87%, respectively. Then, correlation analysis and elastic net were used to determine 12 designing factors for predictive model; At last, four regression techniques, PCR, RF, MLP and SVR were used to develop regression models, respectively; comparison and process analysis of model development were given later. The results show that SVR has the optimal predictive accuracy among four models, its corresponding coefficient of determination can reach to 0.800. This regression model can be utilized to estimate carbon emissions based on designing factors, which can help designers make a strategic decision at early stage.</description><subject>Building lifecycle</subject><subject>Buildings</subject><subject>Carbon</subject><subject>Carbon emissions</subject><subject>Correlation analysis</subject><subject>Decision making</subject><subject>Design</subject><subject>Elastic analysis</subject><subject>Emission measurements</subject><subject>Life cycle analysis</subject><subject>Life cycle assessment</subject><subject>Life cycles</subject><subject>Mathematical analysis</subject><subject>Model accuracy</subject><subject>Prediction models</subject><subject>Predictive model</subject><subject>Regression analysis</subject><subject>Regression models</subject><subject>Residential areas</subject><subject>Residential building</subject><subject>Residential buildings</subject><issn>0378-7788</issn><issn>1872-6178</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNqFUU1v1DAQtSoqsbT8BCRLHLiQxU42dsIFoRVfUiUu5Ww59ng7UdZePAnS_qr-RbxNxZWTnz1v3njeY-yNFFsppPowbiEOC05-WwvZl7e-lf0V28hO15WSunvBNqLRXaV1171kr4hGIYRqtdywx306nmxGSpGnwDMcMhBhuR2Th4l4SJkDzXi0M64cZ_NQEBzxiUjcLxnjgT99oYB3xCcM4M5uAr7QpeSB8BAvKFg3p0wfuS06BJzmxZ_XyYQe4ox2-qdEHCO_RxtHjO_5_gGjvWXXwU4Er5_PG_br65f7_ffq7ue3H_vPd5XbCTFXrfeiLK46bQeldiGodlBd6J1sehC2bt0wuN4NQe7qVkPXtNZr68GJ1grXiOaGvV11Tzn9XooBZkxLjmWkqRvZa9mpRhVWu7JcTkQZgjnl4lQ-GynMJRszmudszCUbs2ZT-j6tfcVh-IOQDTmE6MBjBjcbn_A_Cn8B7zufLQ</recordid><startdate>20191201</startdate><enddate>20191201</enddate><creator>Xikai, Mao</creator><creator>Lixiong, Wang</creator><creator>Jiwei, Li</creator><creator>Xiaoli, Quan</creator><creator>Tongyao, Wu</creator><general>Elsevier B.V</general><general>Elsevier BV</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7ST</scope><scope>8FD</scope><scope>C1K</scope><scope>F28</scope><scope>FR3</scope><scope>KR7</scope><scope>SOI</scope></search><sort><creationdate>20191201</creationdate><title>Comparison of regression models for estimation of carbon emissions during building's lifecycle using designing factors: a case study of residential buildings in Tianjin, China</title><author>Xikai, Mao ; Lixiong, Wang ; Jiwei, Li ; Xiaoli, Quan ; Tongyao, Wu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c400t-5dd0178687ab664ff65b68f9c139e0a25cbbc9cbf14257e835ad7adec05a0c303</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Building lifecycle</topic><topic>Buildings</topic><topic>Carbon</topic><topic>Carbon emissions</topic><topic>Correlation analysis</topic><topic>Decision making</topic><topic>Design</topic><topic>Elastic analysis</topic><topic>Emission measurements</topic><topic>Life cycle analysis</topic><topic>Life cycle assessment</topic><topic>Life cycles</topic><topic>Mathematical analysis</topic><topic>Model accuracy</topic><topic>Prediction models</topic><topic>Predictive model</topic><topic>Regression analysis</topic><topic>Regression models</topic><topic>Residential areas</topic><topic>Residential building</topic><topic>Residential buildings</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Xikai, Mao</creatorcontrib><creatorcontrib>Lixiong, Wang</creatorcontrib><creatorcontrib>Jiwei, Li</creatorcontrib><creatorcontrib>Xiaoli, Quan</creatorcontrib><creatorcontrib>Tongyao, Wu</creatorcontrib><collection>CrossRef</collection><collection>Environment Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Civil Engineering Abstracts</collection><collection>Environment Abstracts</collection><jtitle>Energy and buildings</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xikai, Mao</au><au>Lixiong, Wang</au><au>Jiwei, Li</au><au>Xiaoli, Quan</au><au>Tongyao, Wu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Comparison of regression models for estimation of carbon emissions during building's lifecycle using designing factors: a case study of residential buildings in Tianjin, China</atitle><jtitle>Energy and buildings</jtitle><date>2019-12-01</date><risdate>2019</risdate><volume>204</volume><spage>109519</spage><pages>109519-</pages><artnum>109519</artnum><issn>0378-7788</issn><eissn>1872-6178</eissn><abstract>•Based on the life cycle assessment theory, this paper has estimated and analyzed carbon emissions of 207 residential buildings in Tianjin.•Correlation analysis and elastic net were jointly used to select 12 design factors as independent variables for predictive models.•Four frequently-used regression techniques, PCR, RF, MLP and SVR, were used to develop regression models of carbon emissions.
Many studies have been conducted on life cycle assessment and control measures for carbon emissions of buildings. Methods proposed by these studies usually require not only specific accounting model, but also detailed inventory data, which is not available at early design stage. Seeing that the importance of design phase to carbon emissions during building's lifecycle, a study on regression model of carbon emissions using designing factors was done. Firstly, based on process analysis method, the carbon emissions of 207 residential buildings in Tianjin were calculated. The results show that annual carbon emissions per floor area are between 30 and 60 kgCO2/(m2•year), with manufacture phase and operation phase accounting for 11%–25% and 75%–87%, respectively. Then, correlation analysis and elastic net were used to determine 12 designing factors for predictive model; At last, four regression techniques, PCR, RF, MLP and SVR were used to develop regression models, respectively; comparison and process analysis of model development were given later. The results show that SVR has the optimal predictive accuracy among four models, its corresponding coefficient of determination can reach to 0.800. This regression model can be utilized to estimate carbon emissions based on designing factors, which can help designers make a strategic decision at early stage.</abstract><cop>Lausanne</cop><pub>Elsevier B.V</pub><doi>10.1016/j.enbuild.2019.109519</doi></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0378-7788 |
ispartof | Energy and buildings, 2019-12, Vol.204, p.109519, Article 109519 |
issn | 0378-7788 1872-6178 |
language | eng |
recordid | cdi_proquest_journals_2319718636 |
source | Elsevier ScienceDirect Journals Complete |
subjects | Building lifecycle Buildings Carbon Carbon emissions Correlation analysis Decision making Design Elastic analysis Emission measurements Life cycle analysis Life cycle assessment Life cycles Mathematical analysis Model accuracy Prediction models Predictive model Regression analysis Regression models Residential areas Residential building Residential buildings |
title | Comparison of regression models for estimation of carbon emissions during building's lifecycle using designing factors: a case study of residential buildings in Tianjin, China |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-14T05%3A10%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Comparison%20of%20regression%20models%20for%20estimation%20of%20carbon%20emissions%20during%20building's%20lifecycle%20using%20designing%20factors:%20a%20case%20study%20of%20residential%20buildings%20in%20Tianjin,%20China&rft.jtitle=Energy%20and%20buildings&rft.au=Xikai,%20Mao&rft.date=2019-12-01&rft.volume=204&rft.spage=109519&rft.pages=109519-&rft.artnum=109519&rft.issn=0378-7788&rft.eissn=1872-6178&rft_id=info:doi/10.1016/j.enbuild.2019.109519&rft_dat=%3Cproquest_cross%3E2319718636%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2319718636&rft_id=info:pmid/&rft_els_id=S0378778819313672&rfr_iscdi=true |