What question did this study set out to answer?

The aim is to develop a framework that accurately predicts energy and carbon performance of office buildings during early design stages.

February 8, 2026Open Access

Integrating BIM and Machine Learning for Energy and Carbon Performance Prediction in Office Building Design

Puntos clave

The aim is to develop a framework that accurately predicts energy and carbon performance of office buildings during early design stages.
Developed a BIM-ML framework for energy and carbon performance prediction
Conducted a Design of Experiments (DOE) generating 210 office building models
Employed four regression methods for predictive analysis
Utilized 10-fold cross-validation for model evaluation
Performed feature-importance analysis to identify key parameters
Random Forest exhibited the strongest predictive performance compared to other methods
HVAC system type and Window-to-Wall Ratio were identified as the most significant parameters
Framework validated against actual data from two university buildings, demonstrating adaptability
Cross-climate analysis supports generalization of the framework in various scenarios

Resumen

Accurate early-stage assessment of building energy and carbon performance is essential for informed sustainable design yet remains challenging due to limited design detail and simulation effort. This study presents a Building Information Modeling–Machine Learning (BIM-ML) framework for predicting office building energy and carbon performance at early design stages using simulation-based datasets. A reduced-factorial Design of Experiments (DOE) generated 210 parametric office building models for Orlando, Florida (ASHRAE Climate Zone 2A), complemented by additional climate scenarios. Systematic variations in geometry, envelope, building systems, and operational schedules produced a dataset with 14 independent variables and five performance indicators: Energy Use Intensity, Operational Energy, Operational Carbon, Embodied Carbon, and Total Carbon. Four regression methods—Linear Regression, Model Tree (M5P), Sequential Minimal Optimization Regression, and Random Forest—were trained and evaluated using 10-fold cross-validation. Random Forest showed the strongest overall predictive performance. Feature-importance analysis identified HVAC system type, Window-to-Wall Ratio, and operational schedule as the most influential parameters, while geometric factors had lower impact. Cross-climate analysis and validation with measured data from two university office buildings indicate that the framework is adaptable and generalizable, supporting reliable early-stage evaluation of energy and carbon performance.

Me gusta

Guardar

Ver artículo completo