{"title":"绘制美国家庭能源脆弱性:来自统计和机器学习分析的新见解","authors":"Raphael Apeaning , Musah Labaran , Mohammed Osman","doi":"10.1016/j.erss.2025.104342","DOIUrl":null,"url":null,"abstract":"<div><div>We deploy a two-stage, theory-driven framework to diagnose household energy vulnerability in the United States using the 2020 Residential Energy Consumption Survey. The first step employs a Latent Class Analysis with covariates to extract three capability-based profiles—Secured, Cost-Stressed, and Vulnerable—within a single, coherent likelihood framework. The second step fits a LightGBM model interpreted through SHapley Additive exPlanations (SHAP) to rank the underlying drivers behind each profile. Households earning < $50,000, living in poorly insulated single-family homes, and exposed to high regional energy prices are most likely to fall into the Vulnerable class. The risk intensifies for larger, Black, and female-headed households and for those residing in climates with high heating or cooling degree-day loads. The Cost-Stressed class is driven mainly by large floor area, “other rental” tenure, and moderate incomes ($50,000–$74,999); inadequate insulation and employment insecurity further elevate risk. These findings expose the heterogeneity of U.S. energy hardship and identify distinct leverage points for policy. Embedding such differentiated strategies within federal and state energy-justice initiatives can more equitably reduce household energy burdens and advance capability-based well-being across demographic and regional lines.</div></div>","PeriodicalId":48384,"journal":{"name":"Energy Research & Social Science","volume":"129 ","pages":"Article 104342"},"PeriodicalIF":7.4000,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Mapping household energy vulnerabilities in the United States: New insights from statistical and machine learning analyses\",\"authors\":\"Raphael Apeaning , Musah Labaran , Mohammed Osman\",\"doi\":\"10.1016/j.erss.2025.104342\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>We deploy a two-stage, theory-driven framework to diagnose household energy vulnerability in the United States using the 2020 Residential Energy Consumption Survey. The first step employs a Latent Class Analysis with covariates to extract three capability-based profiles—Secured, Cost-Stressed, and Vulnerable—within a single, coherent likelihood framework. The second step fits a LightGBM model interpreted through SHapley Additive exPlanations (SHAP) to rank the underlying drivers behind each profile. Households earning < $50,000, living in poorly insulated single-family homes, and exposed to high regional energy prices are most likely to fall into the Vulnerable class. The risk intensifies for larger, Black, and female-headed households and for those residing in climates with high heating or cooling degree-day loads. The Cost-Stressed class is driven mainly by large floor area, “other rental” tenure, and moderate incomes ($50,000–$74,999); inadequate insulation and employment insecurity further elevate risk. These findings expose the heterogeneity of U.S. energy hardship and identify distinct leverage points for policy. Embedding such differentiated strategies within federal and state energy-justice initiatives can more equitably reduce household energy burdens and advance capability-based well-being across demographic and regional lines.</div></div>\",\"PeriodicalId\":48384,\"journal\":{\"name\":\"Energy Research & Social Science\",\"volume\":\"129 \",\"pages\":\"Article 104342\"},\"PeriodicalIF\":7.4000,\"publicationDate\":\"2025-09-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Energy Research & Social Science\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2214629625004232\",\"RegionNum\":2,\"RegionCategory\":\"经济学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENVIRONMENTAL STUDIES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy Research & Social Science","FirstCategoryId":"96","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2214629625004232","RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL STUDIES","Score":null,"Total":0}
Mapping household energy vulnerabilities in the United States: New insights from statistical and machine learning analyses
We deploy a two-stage, theory-driven framework to diagnose household energy vulnerability in the United States using the 2020 Residential Energy Consumption Survey. The first step employs a Latent Class Analysis with covariates to extract three capability-based profiles—Secured, Cost-Stressed, and Vulnerable—within a single, coherent likelihood framework. The second step fits a LightGBM model interpreted through SHapley Additive exPlanations (SHAP) to rank the underlying drivers behind each profile. Households earning < $50,000, living in poorly insulated single-family homes, and exposed to high regional energy prices are most likely to fall into the Vulnerable class. The risk intensifies for larger, Black, and female-headed households and for those residing in climates with high heating or cooling degree-day loads. The Cost-Stressed class is driven mainly by large floor area, “other rental” tenure, and moderate incomes ($50,000–$74,999); inadequate insulation and employment insecurity further elevate risk. These findings expose the heterogeneity of U.S. energy hardship and identify distinct leverage points for policy. Embedding such differentiated strategies within federal and state energy-justice initiatives can more equitably reduce household energy burdens and advance capability-based well-being across demographic and regional lines.
期刊介绍:
Energy Research & Social Science (ERSS) is a peer-reviewed international journal that publishes original research and review articles examining the relationship between energy systems and society. ERSS covers a range of topics revolving around the intersection of energy technologies, fuels, and resources on one side and social processes and influences - including communities of energy users, people affected by energy production, social institutions, customs, traditions, behaviors, and policies - on the other. Put another way, ERSS investigates the social system surrounding energy technology and hardware. ERSS is relevant for energy practitioners, researchers interested in the social aspects of energy production or use, and policymakers.
Energy Research & Social Science (ERSS) provides an interdisciplinary forum to discuss how social and technical issues related to energy production and consumption interact. Energy production, distribution, and consumption all have both technical and human components, and the latter involves the human causes and consequences of energy-related activities and processes as well as social structures that shape how people interact with energy systems. Energy analysis, therefore, needs to look beyond the dimensions of technology and economics to include these social and human elements.