Carlo Schmid, Fabian Kastner, Dachuan Zhang, Silke Langenberg, Stefanie Hellweg
{"title":"使用大型语言模型和建筑历史的瑞士外墙材料库存的时空映射","authors":"Carlo Schmid, Fabian Kastner, Dachuan Zhang, Silke Langenberg, Stefanie Hellweg","doi":"10.1111/jiec.70058","DOIUrl":null,"url":null,"abstract":"<p>Building material stock studies are essential for advancing the circular economy in construction. However, existing models often lack both accuracy and scalability. While machine learning has demonstrated significant potential to enhance predictive accuracy, its adoption has been hindered by a shortage of high-quality training data. In this study, we introduce a novel methodology leveraging a large language model to extract previously untapped building material data from building energy performance certificates with a focus on exterior walls. This approach enabled us to create a dataset of over 20,000 buildings—significantly larger than those used in previous studies. Leveraging this dataset, we developed a machine learning model to predict material composition based on building characteristics such as construction year, use, and location. Furthermore, we integrated knowledge of construction history to estimate the material stock of walls in terms of volume, mass, and associated CO<sub>2</sub> emissions for each building in the dataset. Our analysis revealed significant regional variations in material use patterns, emphasizing the critical role of location—a parameter often overlooked in existing building material stock models. These findings provide valuable insights for improving building stock modeling and highlight the importance of regionally tailored policies in advancing the circular economy in the construction sector.</p>","PeriodicalId":16050,"journal":{"name":"Journal of Industrial Ecology","volume":"29 4","pages":"1350-1363"},"PeriodicalIF":5.4000,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/jiec.70058","citationCount":"0","resultStr":"{\"title\":\"Spatiotemporal mapping of Swiss exterior wall material stock using a large language model and architectural history\",\"authors\":\"Carlo Schmid, Fabian Kastner, Dachuan Zhang, Silke Langenberg, Stefanie Hellweg\",\"doi\":\"10.1111/jiec.70058\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Building material stock studies are essential for advancing the circular economy in construction. However, existing models often lack both accuracy and scalability. While machine learning has demonstrated significant potential to enhance predictive accuracy, its adoption has been hindered by a shortage of high-quality training data. In this study, we introduce a novel methodology leveraging a large language model to extract previously untapped building material data from building energy performance certificates with a focus on exterior walls. This approach enabled us to create a dataset of over 20,000 buildings—significantly larger than those used in previous studies. Leveraging this dataset, we developed a machine learning model to predict material composition based on building characteristics such as construction year, use, and location. Furthermore, we integrated knowledge of construction history to estimate the material stock of walls in terms of volume, mass, and associated CO<sub>2</sub> emissions for each building in the dataset. Our analysis revealed significant regional variations in material use patterns, emphasizing the critical role of location—a parameter often overlooked in existing building material stock models. These findings provide valuable insights for improving building stock modeling and highlight the importance of regionally tailored policies in advancing the circular economy in the construction sector.</p>\",\"PeriodicalId\":16050,\"journal\":{\"name\":\"Journal of Industrial Ecology\",\"volume\":\"29 4\",\"pages\":\"1350-1363\"},\"PeriodicalIF\":5.4000,\"publicationDate\":\"2025-06-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1111/jiec.70058\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Industrial Ecology\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/jiec.70058\",\"RegionNum\":3,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, ENVIRONMENTAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Industrial Ecology","FirstCategoryId":"93","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/jiec.70058","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}
Spatiotemporal mapping of Swiss exterior wall material stock using a large language model and architectural history
Building material stock studies are essential for advancing the circular economy in construction. However, existing models often lack both accuracy and scalability. While machine learning has demonstrated significant potential to enhance predictive accuracy, its adoption has been hindered by a shortage of high-quality training data. In this study, we introduce a novel methodology leveraging a large language model to extract previously untapped building material data from building energy performance certificates with a focus on exterior walls. This approach enabled us to create a dataset of over 20,000 buildings—significantly larger than those used in previous studies. Leveraging this dataset, we developed a machine learning model to predict material composition based on building characteristics such as construction year, use, and location. Furthermore, we integrated knowledge of construction history to estimate the material stock of walls in terms of volume, mass, and associated CO2 emissions for each building in the dataset. Our analysis revealed significant regional variations in material use patterns, emphasizing the critical role of location—a parameter often overlooked in existing building material stock models. These findings provide valuable insights for improving building stock modeling and highlight the importance of regionally tailored policies in advancing the circular economy in the construction sector.
期刊介绍:
The Journal of Industrial Ecology addresses a series of related topics:
material and energy flows studies (''industrial metabolism'')
technological change
dematerialization and decarbonization
life cycle planning, design and assessment
design for the environment
extended producer responsibility (''product stewardship'')
eco-industrial parks (''industrial symbiosis'')
product-oriented environmental policy
eco-efficiency
Journal of Industrial Ecology is open to and encourages submissions that are interdisciplinary in approach. In addition to more formal academic papers, the journal seeks to provide a forum for continuing exchange of information and opinions through contributions from scholars, environmental managers, policymakers, advocates and others involved in environmental science, management and policy.