AI-Driven Multi-Objective Optimization of Urban Building Morphology for Climate-Responsive Architectural Design

Authors

  • Gaja Harasimiuk Department of Computer Science, George Mason University, Fairfax, VA, USA.; Maida Usada; School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, OR, USA. Author

Keywords:

urban building morphology; climate-responsive design; multi-objective optimization; surrogate modeling; hypervolume; uncertainty quantification

Abstract

Urban building morphology is a first-order control on solar access, daylight, ventilation, and operational energy, yet climate-responsive design must reconcile conflicting objectives under site, regulatory, and structural constraints. This manuscript develops an AI-driven multi-objective optimization framework for urban building morphology that treats design as a constrained, simulation-based, many-criteria decision problem rather than a single-score search. The framework encodes footprints, heights, orientation, setbacks, and porosity as mixed design variables; maps morphology and climate-scenario inputs to energy demand, thermal discomfort, daylight availability, and solar potential through probabilistic surrogate models; and couples surrogate inference with Pareto-based evolutionary search and hypervolume-based batch selection. Uncertainty from surrogate error, weather variability, and model assumptions is propagated into robust compromise selection, so that recommended morphologies are evaluated by both predicted performance and predictive variance. The contribution is methodological: it clarifies how AI surrogates, physical performance metrics, and multi-objective decision rules can be joined without reducing urban climate performance to a single objective or treating machine-learning predictions as ground truth. The framework also specifies validation logic, constraint handling, and failure modes, including extrapolation under novel morphologies and smoothing of shadow boundaries. The approach supports early-stage architectural and urban design by producing transparent Pareto sets and uncertainty-aware recommendations, while retaining simulation-based evaluation for final verification. It is relevant to climate-responsive master planning, district-scale retrofit, and performance-based design review.

References

1. Oke, T. R., Mills, G., Christen, A., & Voogt, J. A. (2017). Urban climates. Cambridge University Press.

2. Santamouris, M. (2014). Cooling the cities – A review of reflective and green roof mitigation technologies to fight heat island and improve comfort in urban environments. Solar Energy, 103, 682–703.

3. Reinhart, C. F., & Cerezo, C. (2016). Urban building energy modeling – A review of a nascent field. Building and Environment, 97, 196–202.

4. Evins, R. (2013). A review of computational optimisation methods applied to sustainable building design. Renewable and Sustainable Energy Reviews, 22, 230–245.

5. Tabasi, S. F., Luo, D., Rafizadeh, H. R., Le Nguyen, K., & Banihashemi, S. (2025). Generative optimization of building blocks for density, solar and structural performance. Journal of Building Engineering, 111, 113307.

6. Machairas, V., Tsangrassoulis, A., & Axarli, K. (2014). Algorithms for optimization of building design: A review. Renewable and Sustainable Energy Reviews, 31, 101–112.

7. 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.

8. 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.

9. Zitzler, E., & Thiele, L. (1999). Multiobjective evolutionary algorithms: A comparative case study and the strength Pareto approach. IEEE Transactions on Evolutionary Computation, 3(4), 257–271.

10. Emmerich, M. T. M., & Deutz, A. H. (2018). A tutorial on multiobjective optimization: Fundamentals and evolutionary methods. Natural Computing, 17(3), 585–609.

11. Rasmussen, C. E., & Williams, C. K. I. (2006). Gaussian processes for machine learning. MIT Press.

12. Jones, D. R., Schonlau, M., & Welch, W. J. (1998). Efficient global optimization of expensive black-box functions. Journal of Global Optimization, 13(4), 455–492.

13. Westermann, P., & Evins, R. (2019). Surrogate modelling for sustainable building design – A review. Energy and Buildings, 198, 170–186.

14. Compagnon, R. (2004). Solar and daylight availability in the urban fabric. Energy and Buildings, 36(4), 321–328.

15. Hopfe, C. J., & Hensen, J. L. M. (2011). Uncertainty analysis in building performance simulation for design support. Energy and Buildings, 43(10), 2798–2805.

16. Bader, J., & Zitzler, E. (2011). HypE: An algorithm for fast hypervolume-based many-objective optimization. Evolutionary Computation, 19(1), 45–76.

17. Ratti, C., Raydan, D., & Steemers, K. (2003). Building form and environmental performance: Archetypes, analysis and an arid climate. Energy and Buildings, 35(1), 49–59.

18. Moonen, P., Defraeye, T., Dorer, V., Blocken, B., & Carmeliet, J. (2012). Urban physics: Effect of the micro-climate on comfort, health and energy demand. Frontiers of Architectural Research, 1(3), 197–228.

19. Crawley, D. B., Hand, J. W., Kummert, M., & Griffith, B. T. (2008). Contrasting the capabilities of building energy performance simulation programs. Building and Environment, 43(4), 661–673.

20. Shi, X., Tian, Z., Chen, W., Si, B., & Jin, X. (2016). A review on building energy efficient design optimization from the perspective of architects. Renewable and Sustainable Energy Reviews, 65, 872–884.

Downloads

Published

2026-10-04