Machine Learning–Based Optimization of a Health Facility Design
Keywords:
Machine Learning (ML), Building Information Modeling (BIM), Energy Efficiency, Thermal Comfort, Daylight Autonomy, Natural Ventilation, Parametric Design, Architectural Optimization, Smart BuildingsAbstract
This Study presents a machine learning–driven optimization of a 4000 sqft mental health rehabilitation facility. Using a Building Information Model (BIM) from Autodesk Revit as the design data source, we integrated AI-based python analytical tools to optimize key architectural and performance parameters, including spatial layout efficiency, natural lighting, thermal comfort, and ventilation effectiveness. A custom workflow combined Revit’s parametric modeling capabilities with generative design algorithms and optimization using a genetic algorithm models to rapidly explore design solutions and predict building performance. The final optimized design – selected from hundreds of AI-evaluated alternatives – demonstrates significant performance gains over the baseline: daylight availability increased by over 60%, thermal comfort hours by 20%, natural ventilation potential more than doubled, and annual energy use dropped by about 33%. Analytical results for the optimized design are presented with detailed tables and graphs, and we discuss how the ML-based approach balanced multiple objectives to achieve a high-performance, climate-responsive facility. The paper highlights the seamless integration between Revit and AI tools, illustrating a forward-looking approach to data-driven architectural design optimization.
Downloads
References
Attia, S., Gratia, E., De Herde, A., & Hensen, J. L. M. (2012). Simulation-based decision support tool for early stages of zero-energy building design. Energy and Buildings, 49, 2–15. https://doi.org/10.1016/j.enbuild.2012.01.028
Nguyen, A. T., Reiter, S., & Rigo, P. (2014). A review on simulation-based optimization methods applied to building performance analysis. Applied Energy, 113, 1043–1058. https://doi.org/10.1016/j.apenergy.2013.08.061
Asadi, E., da Silva, M. G., Antunes, C. H., & Dias, L. (2012). Multi-objective optimization for building retrofit strategies: A model and an application. Energy and Buildings, 44, 81–87.
Dogan, T., & Reinhart, C. F. (2017). Shoeboxer: An algorithm for abstracted rapid multi-zone urban building energy model generation and simulation. Energy and Buildings, 140, 140–153.
Welle, B., Rogers, Z., & Coley, D. A. (2019). Design space exploration of nearly zero energy buildings: Parametric multi-objective optimization for a hybrid passive and active system design. Renewable Energy, 130, 933–945.
Autodesk. (2020). Insight Energy Analysis with Revit. Retrieved from https://knowledge.autodesk.com/support/insight
Zuo, W., & Zhao, Y. (2014). CFD simulation of air distribution in buildings: A review. Indoor and Built Environment, 23(3), 357–369.
Zhang, Y., Korolija, I., & Hanby, V. I. (2012). Whole-building energy modelling and simulation: A state-of-the-art review. Renewable and Sustainable Energy Reviews, 16(6), 4067–4079.
Gerber, D. J., Lin, S., Pan, B., Solmaz, A. S., & Solmaz, Y. (2020). Design Optioneering and Performance Feedback with Revit, Dynamo, and Project Refinery. Journal of Information Technology in Construction, 25, 77–89.
Ma, Y., Wu, L., Wang, Y., & Ding, Y. (2021). Reinforcement Learning Applications in Smart Buildings: A Review. Renewable and Sustainable Energy Reviews, 145, 111078.
Jiang, Z., Wang, X., Li, H., Hong, T., You, F., Drgoňa, J., Vrabie, D., & Dong, B. (2025). Physics-informed machine learning for building performance simulation—A review of a nascent field. arXiv preprint arXiv:2504.00937.sciencedirect.com+2arxiv.org+2arxiv.org+2
Papadopoulos, S., Woon, W. L., & Azar, E. (2018). Machine Learning as Surrogate to Building Performance Simulation: A Building Design Optimization Application. In Data Analytics for Renewable Energy Integration (pp. 111–125). Springer.link.springer.com+1sciencedirect.com+1
Chakraborty, D., & Elzarka, H. (2019). Advanced machine learning techniques for building performance simulation: A comparative analysis. Journal of Building Performance Simulation, 12(2), 193–207.researchgate.net
He, Z., Wang, Y.-H., & Zhang, J. (2023). Generative AIBIM: An automatic and intelligent structural design pipeline integrating BIM and generative AI. arXiv preprint arXiv:2311.04052.arxiv.org
Aijazi, A. N. (2017). Machine learning paradigms for building energy performance simulations. Massachusetts Institute of Technology.dspace.mit.edu
Mostafa, A., & Safour, R. (2023). Application of Artificial Intelligence Tools with BIM Technology in Construction Management: Literature Review. ResearchGate.researchgate.net
Hudson, M., & Vannini, A. (2015). Dynamo Hero: Using Revit Scripting Tools to Optimize Real-World Projects. Autodesk University.static.au-uw2-prd.autodesk.com+1static.au-uw2-prd.autodesk.com+1
Ringley, M. (2015). Dynamo + Rhynamo: Synchronous Design + Documentation Case Studies. Autodesk University.static.au-uw2-prd.autodesk.com
Reope. (n.d.). Autodesk - Case Study by Reope. Retrieved from https://www.reope.com/case-studies/autodeskreope.com
KTH Royal Institute of Technology. (2016). Parametric BIM: Energy Performance Analysis Using Dynamo for Revit. DiVA Portal.core.ac.uk+2diva-portal.org+2kth.diva-portal.org+2
MDPI. (2024). Using Dynamo for Automatic Reconstruction of BIM Elements from Point Clouds. Applied Sciences, 14(10), 4078.mdpi.com
Autodesk. (2024). Automated and Parametrized Reinforcement Workflow: Case Studies of Infrastructure Projects Using Templates. Autodesk University.autodesk.com
Suphavarophas, P., Wongmahasiri, R., Keonil, N., & Bunyarittikit, S. (2024). A Systematic Review of Applications of Generative Design Methods for Energy Efficiency in Buildings. Buildings.en.wikipedia.org
Das, H. P., Lin, Y.-W., Agwan, U., Spangher, L., Devonport, A., Yang, Y., Drgona, J., Chong, A., Schiavon, S., & Spanos, C. J. (2022). Machine Learning for Smart and Energy-Efficient Buildings. arXiv preprint arXiv:2211.14889.arxiv.org
Qolomany, B., Al-Fuqaha, A., Gupta, A., Benhaddou, D., Alwajidi, S., Qadir, J., & Fong, A. C. (2019). Leveraging Machine Learning and Big Data for Smart Buildings: A Comprehensive Survey. arXiv preprint arXiv:1904.01460.arxiv.org
Chakraborty, D., & Elzarka, H. (2019). Advanced machine learning techniques for building performance simulation: A comparative analysis. Journal of Building Performance Simulation, 12(2), 193–207.researchgate.net
Zhang, Y., Korolija, I., & Hanby, V. I. (2012). Whole-building energy modelling and simulation: A state-of-the-art review. Renewable and Sustainable Energy Reviews, 16(6), 4067–4079.
Dogan, T., & Reinhart, C. F. (2017). Shoeboxer: An algorithm for abstracted rapid multi-zone urban building energy model generation and simulation. Energy and Buildings, 140, 140–153.
Welle, B., Rogers, Z., & Coley, D. A. (2019). Design space exploration of nearly zero energy buildings: Parametric multi-objective optimization for a hybrid passive and active system design. Renewable Energy, 130, 933–945.
Attia, S., Gratia, E., De Herde, A., & Hensen, J. L. M. (2012). Simulation-based decision support tool for early stages of zero-energy building design. Energy and Buildings, 49, 2–15.
Nguyen, A. T., Reiter, S., & Rigo, P. (2014). A review on simulation-based optimization methods applied to building performance analysis. Applied Energy, 113, 1043–1058.
Asadi, E., da Silva, M. G., Antunes, C. H., & Dias, L. (2012). Multi-objective optimization for building retrofit strategies: A model and an application. Energy and Buildings, 44, 81–87.
Zuo, W., & Zhao, Y. (2014). CFD simulation of air distribution in buildings: A review. Indoor and Built Environment, 23(3), 357–369.
Coakley, D., Raftery, P., & Keane, M. (2014). A review of methods to match building energy simulation models to measured data. Renewable and Sustainable Energy Reviews, 37, 123–141. https://doi.org/10.1016/j.rser.2014.05.007
Evins, R. (2013). A review of computational optimisation methods applied to sustainable building design. Renewable and Sustainable Energy Reviews, 22, 230–245. https://doi.org/10.1016/j.rser.2013.02.004
Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), 182–197. https://doi.org/10.1109/4235.996017
Kaushik, A., Rajput, S., & Aggarwal, S. (2023). Machine Learning in Smart Buildings: A Survey. International Journal of Computer Applications, 175(32), 12–18.
Tian, W. (2013). A review of sensitivity analysis methods in building energy analysis. Renewable and Sustainable Energy Reviews, 20, 411–419. https://doi.org/10.1016/j.rser.2012.12.014
Wetter, M., Zuo, W., Nouidui, T. S., & Pang, X. (2011). Modelica Buildings Library. Journal of Building Performance Simulation, 4(4), 319–330. https://doi.org/10.1080/19401493.2010.549572
Kazanci, O. B., & Olesen, B. W. (2016). Impact of the indoor environment on occupants’ productivity: A review. International Journal of Ventilation, 15(2), 115–128.
Capozzoli, A., Gorrino, A., & Corrado, V. (2013). A building thermal bridges sensitivity analysis for the optimization of envelope design. Energy and Buildings, 67, 792–800. https://doi.org/10.1016/j.enbuild.2013.08.001
Wang, C., Chen, Q., & Zhai, Z. J. (2010). Evaluation of various turbulence models in predicting airflow and turbulence in enclosed environments by CFD. Building and Environment, 45(2), 519–527.
Reinhart, C. F., & Fitz, A. (2006). Findings from a survey on the current use of daylight simulations in building design. Energy and Buildings, 38(7), 824–835.
Oldewurtel, F., Parisio, A., Jones, C. N., Gyalistras, D., Gwerder, M., Stauch, V., ... & Morari, M. (2012). Use of model predictive control and weather forecasts for energy efficient building climate control. Energy and Buildings, 45, 15–27.
Cerezo, C., Sokol, J., Al Mumin, A., & Reinhart, C. F. (2017). Comparison of four building design strategies to maximize thermal comfort and energy performance in Kuwait’s residential sector. Building Simulation, 10(5), 641–658.
Yu, Z., Haghighat, F., Fung, B. C. M., & Zhou, L. (2010). A review of state-of-the-art models and their application for short-term building energy prediction. Renewable and Sustainable Energy Reviews, 13(6–7), 1816–1824.
Bracklow, L., & Braunes, D. (2020). Reinforcement learning for space layout optimization. In Proceedings of the 38th eCAADe Conference.
Shadram, F., Johansson, T., Mukkavaara, J., & Olofsson, T. (2021). Data-driven decision support system for early-stage building design: Integrating BIM and machine learning. Automation in Construction, 124, 103562.
D’Oca, S., Hong, T., & Langevin, J. (2018). The human dimensions of energy use in buildings: A review. Renewable and Sustainable Energy Reviews, 81, 731–742.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
