Deciphering the nonlinear and synergistic role of building energy variables in shaping carbon emissions: A LightGBM- SHAP framework in office buildings

Abstract

As the global demand for sustainable buildings continues to rise, accurately assessing and managing carbon emissions during the operational phase of buildings has become an urgent challenge. This study employs machine learning and Explainable Artificial Intelligence (XAI) to explore the impact and synergistic effects of energy variables on carbon emissions in office building operations. Initially, energy consumption data from 28 office buildings in China were collected to construct a dataset comprising 24 energy indicators across four dimensions. The Lightweight Gradient Boosting Machine (LightGBM) and Extreme Gradient Boosting (XGBoost) models were used to predict building carbon emission, PV carbon offset, and net carbon emission based on different energy parameters. The SHapley Additive exPlanations (SHAP) method was utilized to interpret the model results from both global and local perspectives. The study results indicate that: (1) The LightGBM model, optimized with GridSearchCV, shows better stability and reliability in predicting carbon emissions. (2) SHAP bar plots和SHAP beeswarm plots reveal that the WWR in the ES dimension and the PVArea in the EP dimension are the most critical variables affecting building carbon emission and PV carbon offset. (3) SHAP dependence plots show that the contributions of energy variables are not independent, with differentiated synergistic effects among variables in emission reduction. (4) SHAP force plots consider interactions among multiple variables, identifying key variable ranges to minimize building carbon emission and maximize PV carbon offset.