Sustainable Design of Free-Form Architectural Shells Using Machine Learning and Parametric Optimisation: A Case Study of the Rhike Park Music Theatre
DOI:
https://doi.org/10.38027/jsalutogenic_vol5no1_1Keywords:
Parametric Design, Computational Optimisation, Neural Network Emulator, Façade Panelisation, Form-FindingAbstract
Free-form architectural envelopes are visually striking but notoriously difficult and costly to build. This study explores how computational tools can make such designs more sustainable and constructible, using the Rhike Park Music Theatre in Tbilisi, Georgia, as a case study. The building's double-curved surfaces were reconstructed in Rhino/Grasshopper, and its façade was rationalised into a triangulated panel system. An evolutionary algorithm (Galapagos) first identified optimal panel configurations by balancing material use against fabrication simplicity. A neural network emulator, trained on 500 parametric simulations, was used to optimise the panelisation process. The final design achieved an approximately 40% reduction in surface area, 55.6% fewer unique panel types, and retained 95% of the original interior volume. The proposed workflow demonstrates how ANN-based surrogate modelling can accelerate free-form façade optimisation while maintaining geometric performance and manufacturability, contributing a computational framework for efficient design-space exploration.
Downloads
References
Afzal, A., Kim, K.-Y., & Seo, J. (2017). Effects of Latin hypercube sampling on surrogate modeling and optimization. International Journal of Fluid Machinery and Systems, 10(3), 240–253. https://doi.org/10.5293/IJFMS.2017.10.3.240
Alic, V., & Persson, K. (2016). Form finding with dynamic relaxation and isogeometric membrane elements. Computer Methods in Applied Mechanics and Engineering, 300, 734–747. https://doi.org/10.1016/j.cma.2015.12.009
Araújo, G. R., Gomes, R., Gomes, M. G., Guedes, M. C., & Ferrão, P. (2023). Surrogate Models for Efficient Multi-Objective Optimization of Building Performance. Energies, 16(10), 4030. https://doi.org/10.3390/en16104030
Austern, G., Capeluto, I. G., & Grobman, Y. J. (2018). Rationalization methods in computer aided fabrication: A critical review. Automation in Construction, 90, 281–293. https://doi.org/10.1016/j.autcon.2017.12.027
Barnes, M. R. (1999). Form Finding and Analysis of Tension Structures by Dynamic Relaxation. International Journal of Space Structures, 14(2), 89–104. https://doi.org/10.1260/0266351991494722
Bekkouche, S. M. A., Benouaz, T., Cherier, M. K., Hamdani, M., Yaiche, M. R., & Benamrane, N. (2013). Influence of the compactness index to increase the internal temperature of a building in Saharan climate. Energy and Buildings, 66, 678–687. https://doi.org/10.1016/j.enbuild.2013.07.077
Bianchi, S., Andriotis, C., Klein, T., & Overend, M. (2024). Multi-criteria design methods in façade engineering: State-of-the-art and future trends. Building and Environment, 250, 111184. https://doi.org/10.1016/j.buildenv.2024.111184
Castañeda, E., Lauret, B., Lirola, J. M., & Ovando, G. (2015). Free-form architectural envelopes: Digital processes opportunities of industrial production at a reasonable price. Journal of Façade Design and Engineering, 3(1), 1–13. https://doi.org/10.3233/FDE-150031
Chen, X. (2024). Enhancing Estimation and Uncertainty Quantification in Stochastic Optimization: Importance Sampling and Bootstrap Resampling [PhD dissertation, University of California, Davis]. ProQuest Dissertations and Theses Global (Publication No. 31328967).
Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science, 7, e623. https://doi.org/10.7717/peerj-cs.623
D’Amico, B., & Pomponi, F. (2019). A compactness measure of sustainable building forms. Royal Society Open Science, 6(6), 181265. https://doi.org/10.1098/rsos.181265
Deb, C., Dai, Z., & Schlueter, A. (2021). A machine learning-based framework for cost-optimal building retrofit. Applied Energy, 294, 116990. https://doi.org/10.1016/j.apenergy.2021.116990
Deb, K. (2011). Multi-Objective Optimization Using Evolutionary Algorithms: An Introduction. In L. Wang, A. H. C. Ng, & K. Deb (Eds), Multi-objective evolutionary optimisation for product design and manufacturing (pp. 3–34). Springer. https://doi.org/10.1007/978-0-85729-652-8_1
Duran, A., Waibel, C., Piccioni, V., Bickel, B., & Schlueter, A. (2025). A review on artificial intelligence applications for facades. Building and Environment, 269, 112310. https://doi.org/10.1016/j.buildenv.2024.112310
Eigensatz, M., Kilian, M., Schiftner, A., Mitra, N. J., Pottmann, H., & Pauly, M. (2010). Paneling architectural freeform surfaces. ACM SIGGRAPH 2010 Papers, 29(4), 1–10. https://doi.org/10.1145/1833349.1778782
Flöry, S., & Pottmann, H. (2010). Ruled Surfaces for Rationalization and Design in Architecture. ACADIA 10: LIFE in:Formation: On Responsive Information and Variations in Architecture, 103–109. https://doi.org/10.52842/conf.acadia.2010.103
Freimer, M. B., Linderoth, J. T., & Thomas, D. J. (2012). The impact of sampling methods on bias and variance in stochastic linear programs. Computational Optimization and Applications, 51(1), 51–75. https://doi.org/10.1007/s10589-010-9322-x
Fu, C.-W., Lai, C.-F., He, Y., & Cohen-Or, D. (2010). K-set tilable surfaces. ACM Transactions on Graphics, 29(4), 1–6. https://doi.org/10.1145/1778765.1778781
Gołębiowska, M. (2025). Optimizing Glass Panel Geometry for Freeform Architecture: A Curvature-Based Pavilion Study. Buildings, 15(20), 3635. https://doi.org/10.3390/buildings15203635
Gunantara, N. (2018). A review of multi-objective optimization: Methods and its applications. Cogent Engineering, 5(1), 1502242. https://doi.org/10.1080/23311916.2018.1502242
Hinkle, L. E., Wang, J., & Brown, N. C. (2022). Quantifying potential dynamic façade energy savings in early design using constrained optimization. Building and Environment, 221, 109265. https://doi.org/10.1016/j.buildenv.2022.109265
Hodson, T. O. (2022). Root-mean-square error (RMSE) or mean absolute error (MAE): When to use them or not. Geoscientific Model Development, 15(14), 5481–5487. https://doi.org/10.5194/gmd-15-5481-2022
Hornik, K., Stinchcombe, M. B., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359–366. https://doi.org/10.1016/0893-6080(89)90020-8
Jahirul, M. I., Rasul, M. G., Brown, R. J., Senadeera, W., Hosen, M. A., Haque, R., Saha, S. C., & Mahlia, T. M. I. (2021). Investigation of correlation between chemical composition and properties of biodiesel using principal component analysis (PCA) and artificial neural network (ANN). Renewable Energy, 168, 632–646. https://doi.org/10.1016/j.renene.2020.12.078
Kingma, D. P., & Ba, J. (2017). Adam: A Method for Stochastic Optimization (arXiv:1412.6980). arXiv. https://doi.org/10.48550/arXiv.1412.6980
Kistelegdi, I., Horváth, K. R., Storcz, T., & Ercsey, Z. (2022). Building Geometry as a Variable in Energy, Comfort, and Environmental Design Optimization—A Review from the Perspective of Architects. Buildings, 12(1), 69. https://doi.org/10.3390/buildings12010069
Liu, Y., Lee, T.-U., Rezaee Javan, A., Pietroni, N., & Xie, Y. M. (2024). Reducing the Number of Different Faces in Free-Form Surface Approximations Through Clustering and Optimization. Computer-Aided Design, 166, 103633. https://doi.org/10.1016/j.cad.2023.103633
Mahdavinejad, M., Bazazzadeh, H., Mehrvarz, F., Berardi, U., Nasr, T., Pourbagher, S., & Hoseinzadeh, S. (2024). The impact of facade geometry on visual comfort and energy consumption in an office building in different climates. Energy Reports, 11, 1–17. https://doi.org/10.1016/j.egyr.2023.11.021
McKay, M. D., Beckman, R. J., & Conover, W. J. (1979). Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code. Technometrics, 21(2), 239–245. https://doi.org/10.1080/00401706.1979.10489755
Mehrotra, A., & Yi, H. (2023). Effect of adaptive intelligent sampling and machine-learning emulators in surrogate energy modeling of architectural massing. Journal of Building Engineering, 72, 106614. https://doi.org/10.1016/j.jobe.2023.106614
Meng, X., & Karniadakis, G. E. (2020). A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems. Journal of Computational Physics, 401, 109020. https://doi.org/10.1016/j.jcp.2019.109020
Pham, A.-D., Ngo, N.-T., Ha Truong, T. T., Huynh, N.-T., & Truong, N.-S. (2020). Predicting energy consumption in multiple buildings using machine learning for improving energy efficiency and sustainability. Journal of Cleaner Production, 260, 121082. https://doi.org/10.1016/j.jclepro.2020.121082
Pottmann, H., Liu, Y., Wallner, J., Bobenko, A., & Wang, W. (2007). Geometry of Multi-layer Freeform Structures for Architecture. ACM Transactions on Graphics, 26(3), 65. https://doi.org/10.1145/1275808.1276458
Queipo, N. V., Haftka, R. T., Shyy, W., Goel, T., Vaidyanathan, R., & Kevin Tucker, P. (2005). Surrogate-based analysis and optimization. Progress in Aerospace Sciences, 41(1), 1–28. https://doi.org/10.1016/j.paerosci.2005.02.001
Sarker, I. H. (2021). Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Computer Science, 2(3), 160. https://doi.org/10.1007/s42979-021-00592-x
Senatore, G., & Piker, D. (2015). Interactive real-time physics. Computer-Aided Design, 61, 32–41. https://doi.org/10.1016/j.cad.2014.02.007
Topuz, B., & Çakici Alp, N. (2023). Machine learning in architecture. Automation in Construction, 154, 105012. https://doi.org/10.1016/j.autcon.2023.105012
Wang, B., Lu, W., & Zhang, Y. (2025). A graph-enabled parametric modeling approach for façade layout generative design. Journal of Building Engineering, 105, 112481. https://doi.org/10.1016/j.jobe.2025.112481
Wang, H., Pellis, D., Rist, F., Pottmann, H., & Müller, C. (2019). Discrete geodesic parallel coordinates. ACM Transactions on Graphics, 38(6), 1–13. https://doi.org/10.1145/3355089.3356541
Westermann, P., & Evins, R. (2019). Surrogate modelling for sustainable building design – A review. Energy and Buildings, 198, 170–186. https://doi.org/10.1016/j.enbuild.2019.05.057
Yang, S., Lee, S., & Yee, K. (2023). Inverse design optimization framework via a two-step deep learning approach: Application to a wind turbine airfoil. Engineering with Computers, 39(3), 2239–2255. https://doi.org/10.1007/s00366-022-01617-6
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Fatma Alemşah Kumtaş (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
