Decomposition-guided local-global fusion neural network for residential carbon emission prediction

Residential carbon emissions refer to the release of carbon dioxide and other greenhouse gases from residential buildings and related activities. With rapid urbanization and rising residential energy demand, these emissions have become a significant part of global greenhouse gas emissions. This paper proposes a data-driven deep learning model to predict carbon emission trends in China’s residential sector. Using carbon data from January 1, 2022, to August 31, 2024, experiments validate the model’s superior performance in forecasting across various intervals compared to other competitive models. The results indicate excellence in all evaluation metrics. Additionally, policy recommendations are provided based on predictions, offering both scientific and technical support for carbon neutrality goals in the context of global climate change.