Seasonal dynamics in the prediction of household-level energy poverty: A machine learning approach

Energy Policy 2026 Open access

Read full text
Authors: Boram Moon, J. Hong
DOI: 10.1016/j.enpol.2026.115146
Cited by: 2
References: 44

Abstract

• Machine learning predicts seasonal energy poverty using 330,960 household-month data. • Korea's energy poverty is driven mainly by heating-related structural vulnerability. • Income risk groups face summer vulnerability mainly due to socioeconomic limits. • Income risk groups face winter vulnerability mainly due to structural limits. • Double risk groups face persistently high vulnerability across both seasons.

Fields of Study & Subjects

Energy and Environment Impacts Social Acceptance of Renewable Energy Sustainability and Climate Change Governance

Publication details

Journal / source
Energy Policy
Publisher
Elsevier BV
Volume
212
Pages
115146–115146
Publication date
17 February 2026
Language
EN