BIM–AI-Based Prediction of Building Energy Consumption and Life Cycle Carbon Emissions: A Comparative Review

Author

I. Vasudha, K. Himagiri, B. Dilleswararao, B. Sivani, D. Madhavi


Abstract

 The building industry is a large user of energy and emitter of carbon.The emissions are caused by construction materials, building activities, energy consumption, maintenance and demolition.Energy use and carbon emissions are key elements to predict for sustainable building design.Building Information Modelling (BIM) is a digital representation of building geometry and quantity of materials.Artificial Intelligence (AI) can be used to analyze building data and predict building performance.In  the context of BIM, AI, energy prediction and carbon assessment.The studies reviewed cover the following topics: machine learning, BIM-based energy simulation, digital twins and sustainability assessment.The results show that building geometry, orientation, building materials, climate and occupancy affect building performance.When training and validation data is available, machine-learning methods may be used to assist in energy prediction.The quantities generated by BIM can also be used to estimate embodied carbon of construction materials.Estimates of operational carbon can be made with energy use and suitable emission factors.The review led to the development of an integrated BIM–AI approach for building energy and life-cycle carbon assessment.The framework could be used to compare materials and design options at the early planning stage.More case studies are needed to confirm its validity and applicability to Indian buildings.



Keywords

Building Information Modelling (BIM); Artificial Intelligence (AI); Building Energy Consumption; Carbon Emissions; Machine Learning; Embodied Carbon; Operational Carbon.



Full Text:

Download Paper PDF


References


  1. Li, T., Liu, T., Sawyer, A. O., Tang, P., Loftness, V., Lu, Y., & Xie, J. (2024). Benchmarking of building energy and carbon emissions (GECE) and the post-prediction analysis. The Built Environment, 17, 100320.
  2. Amasyali, K., & El-Gohary, N. M. (2018). Review of building energy consumption prediction studies using data. Renew. Sustainable Energy Rev., 81, 1192-1205.
  3. Seyedzadeh, S., Pour Rahimian, F., Glesk, I., & Roper, M. (2018). Review on machine learning approach to building energy consumption and performance estimation. Visualization in Engineering, 6, Article 5. https://doi.org/10.1186/s40327-018-0064-7
  4. Zou, X., Tan, Y., Zhang, G., & Hou, L. (2026). A systematic review on the sustainability analysis of building green retrofit using BIM. Energy & Buildings, 354, 116982.
  5. Geng, L., Li, S., Noroozinejad Farsangi, E., Xu, X., & Tam, V. W. Y. (2026). What are some ways digital technologies decrease construction industry carbon emissions? A systematic review. Energy & Buildings, 350, 116605.

 

Share your valuable work from Social Media Buttons