Generative AI for Sustainable Architectural Design Optimization
DOI:
https://doi.org/10.54691/czaf4b21Keywords:
Generative Design; Artificial Intelligence; Sustainable Architecture; Building Optimization; Evolutionary Algorithms; Surrogate Modeling; GAN.Abstract
This paper examines recent academic research on applying generative AI and computational methods to optimize sustainable architectural design. Buildings account for roughly one-third of global carbon emissions and energy use, especially via HVAC systems. Early-stage design optimization is therefore crucial to improve efficiency and reduce environmental impact. Generative design including evolutionary and parametric algorithms has emerged as a key approach to exploring diverse design options for sustainability. More recently, advanced AI (e.g. machine learning surrogates, GANs, diffusion models) are being incorporated to accelerate and enrich design optimization. This paper systematically survey peer-reviewed literature (2020–2024), focusing on methods (evolutionary algorithms, ML surrogates, GANs), application domains (energy, daylighting, carbon), and performance outcomes. Key findings include evidence that generative design methods can substantially improve energy and thermal performance (e.g. reported reductions of 23–28% and that genetic algorithms remain widely used. Emerging themes include multi-objective optimization (balancing energy, comfort, cost) and use of deep learning (surrogate models, GAN-based generation) to expand design search. We highlight agreements and gaps: consensus on benefits of generative optimization for sustainability, but challenges remain in model explainability, data requirements, and transferability across contexts. The paper identifies that most studies use quantitative simulation-optimization loops, whereas few provide holistic frameworks and conclude that generative AI holds great potential for sustainable architecture design, but future work must address data/ethical challenges and integrate multi-scale, user-involved approaches.
Downloads
References
[1] Abbas, F., Zhang, F., Iqbal, J., Alrefaei, A. F., & Albeshr, M. (2023). Assessing the dimensionality reduction of the geospatial dataset using principal component analysis (PCA) and its impact on the accuracy and performance of ensembled and non-ensembled algorithms.
[2] Bhattacharya, A. (2022). Applied Machine Learning Explainability Techniques: Make ML models explainable and trustworthy for practical applications using LIME, SHAP, and more. Packt Publishing Ltd.
[3] Channi, H. K., Kaur, A., & Kaur, S. (2025). AI‐Driven Generative Design Redefines the Engineering Process. Generative Artificial Intelligence in Finance: Large Language Models, Interfaces, and Industry Use Cases to Transform Accounting and Finance Processes, 327-359.
[4] Chen, R., Zhao, J., Yao, X., Jiang, S., He, Y., Bao, B., & Wang, C. (2023). Generative design of outdoor green spaces based on generative adversarial networks. Buildings, 13(4), 1083.
[5] Chew, Z. X., Wong, J. Y., Tang, Y. H., Yip, C. C., & Maul, T. (2024). Generative design in the built environment. Automation in Construction, 166, 105638.
[6] Du, Y., Jamasb, A. R., Guo, J., Fu, T., Harris, C., Wang, Y., & Blundell, T. L. (2024). Machine learning-aided generative molecular design. Nature Machine Intelligence, 6(6), 589-604.
[7] Gerber, D. J., & Lin, S. H. E. (2014). Designing in complexity: Simulation, integration, and multidisciplinary design optimization for architecture. Simulation, 90(8), 936-959.
[8] Ghafariasl, P., Mahmoudan, A., Mohammadi, M., Nazarparvar, A., Hoseinzadeh, S., Fathali, M., & Garcia, D. A. (2024). Neural network-based surrogate modeling and optimization of a multigeneration system. Applied Energy, 364, 123130.
[9] Han, Y., Shen, L., & Sun, C. (2021). Developing a parametric morphable annual daylight prediction model with improved generalization capability for the early stages of office building design. Building and Environment, 200, 107932.
[10] Huang, C., Zhang, G., Yao, J., Wang, X., Calautit, J. K., Zhao, C., ... & Peng, X. (2022). Accelerated environmental performance-driven urban design with generative adversarial network. Building and Environment, 224, 109575.
[11] Johari, N. H., Alaloul, W. S., & Musarat, M. A. (2025). Recent advancements of life cycle cost analysis of photovoltaic systems: a systematic review. The International Journal of Life Cycle Assessment, 1-41.
[12] Konstantinov, A. V., & Utkin, L. V. (2021). Interpretable machine learning with an ensemble of gradient boosting machines. Knowledge-Based Systems, 222, 106993.
[13] Krzywanski, J., Sosnowski, M., Grabowska, K., Zylka, A., Lasek, L., & Kijo-Kleczkowska, A. (2024). Advanced computational methods for modeling, prediction and optimization—a review. Materials, 17(14), 3521.
[14] Luo, S. L., Shi, X., & Yang, F. (2024). A review of data-driven methods in building retrofit and performance optimization: From the perspective of carbon emission reductions. Energies, 17(18), 4641.
[15] Manmatharasan, P., Bitsuamlak, G., & Grolinger, K. (2025). AI-Driven Design Optimization for Sustainable Buildings: A Systematic Review. Energy and Buildings, 115440.
[16] Mukkavaara, J., & Sandberg, M. (2020). Architectural design exploration using generative design: framework development and case study of a residential block. Buildings, 10(11), 201.
[17] Nagy, D., Villaggi, L., & Benjamin, D. (2018, June). Generative urban design: integrating financial and energy goals for automated neighborhood layout. In Proceedings of the Symposium for Architecture and Urban Design Design, Delft, the Netherlands (pp. 265-274).
[18] Parimbelli, E., Buonocore, T. M., Nicora, G., Michalowski, W., Wilk, S., & Bellazzi, R. (2023). Why did AI get this one wrong?—Tree-based explanations of machine learning model predictions. Artificial intelligence in medicine, 135, 102471.
[19] Razmi, A., Rahbar, M., & Bemanian, M. (2022). PCA-ANN integrated NSGA-III framework for dormitory building design optimization: Energy efficiency, daylight, and thermal comfort. Applied Energy, 305, 117828.
[20] Razmi, A., Rahbar, M., & Bemanian, M. (2022). PCA-ANN integrated NSGA-III framework for dormitory building design optimization: Energy efficiency, daylight, and thermal comfort. Applied Energy, 305, 117828.
[21] Rodrigues, X., Fedynitch, A., Gao, S., Boncioli, D., & Winter, W. (2018). Neutrinos and Ultra-high-energy Cosmic-ray Nuclei from Blazars. The Astrophysical Journal, 854(1), 54.
[22] Sun, Y., Wang, H., Xue, B., Jin, Y., Yen, G. G., & Zhang, M. (2019). Surrogate-assisted evolutionary deep learning using an end-to-end random forest-based performance predictor. IEEE Transactions on Evolutionary Computation, 24(2), 350-364.
[23] Suphavarophas, P., Wongmahasiri, R., Keonil, N., & Bunyarittikit, S. (2024). A Systematic Review of Applications of Generative Design Methods for Energy Efficiency in Buildings. Buildings, 14(5), 1311.
[24] Vermesan, V., & Flueckiger, U. P. (2016). Intelligent, parametrically sustainable architectural design. WIT Transactions on The Built Environment, 161, 93-105.
[25] Wu, A. N., Stouffs, R., & Biljecki, F. (2022). Generative Adversarial Networks in the built environment: A comprehensive review of the application of GANs across data types and scales. Building and Environment, 223, 109477.
[26] Zaini, F. A., Sulaima, M. F., Razak, I. A. W. A., Zulkafli, N. I., & Mokhlis, H. (2023). A review on the applications of PSO-based algorithm in demand side management: challenges and opportunities. IEEE Access, 11, 53373-53400.
[27] Zaraza, J., McCabe, B., Duhamel, M., & Posen, D. (2022). Generative design to reduce embodied GHG emissions of high-rise buildings. Automation in construction, 139, 104274.
[28] Zhang, J., Liu, N., & Wang, S. (2021). Generative design and performance optimization of residential buildings based on parametric algorithm. Energy and Buildings, 244, 111033.
[29] Zhang, R., Xu, X., Liu, K., Kong, L., Wang, X., Zhao, L., & Abuduwayiti, A. (2024). Does architectural design require single-objective or multi-objective optimisation? A critical choice with a comparative study between model-based algorithms and genetic algorithms. Frontiers of Architectural Research, 13(5), 1079-1094.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Scientific Journal of Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
