Leveraging Artificial Intelligence to Translate Computational Simulation Results of Natural Ventilation in Tall Office Buildings into Human-Centered Insights
DOI:
https://doi.org/10.15377/2409-9821.2025.12.18Keywords:
AI-driven visualization, CFD simulation, Airflow behavior, Human experience, Design pedagogyAbstract
Tall office buildings are increasingly designed with sustainability and occupant comfort in mind, and natural ventilation plays a critical role in achieving these goals. However, their height and exposure to complex, variable wind conditions introduce significant challenges, often producing uneven airflow patterns that limit effective air movement and directly affect human experience and behavior. Computational simulations are widely used to analyze the natural ventilation potential in buildings, as they provide comprehensive information on airflow behavior. Velocity contour visualizations quantify airflow distribution, yet their direct translation into human experiential and behavioral understanding remains limited, despite their interpretive insights. This study presents a visualization method using Artificial Intelligence (AI) to translate computational simulation results into design-oriented visualizations, including atmospheric diagrams and collages, that communicate relative experiential and behavioral tendencies rather than precise predictions of human behavior. AI serves as the primary tool, generating interpretable visualizations from prompts composed of keywords representing airflow behavior and insights derived from selected published simulation results on natural ventilation in tall office buildings. The proposed framework bridges quantitative technical data and experiential interpretation through a structured, two-stage embedding process, allowing airflow distributions and associated emotional and behavioral responses to be represented visually. The resulting images emphasize perceptual legibility and comparative interpretation to support design reasoning and pedagogy. Limited to simplified airflow conditions and experiential indicators, the framework provides an early-stage method that supports design exploration, architectural education, and communication by integrating quantitative analysis, qualitative experience, and architectural representation into a coherent visual reasoning process.
Downloads
References
[1] Kim Y, Heidarinejad M, Elnimeiri M. Integrated numerical framework to assess double-skin façade configurations for wind-driven natural ventilation in tall office buildings. J Archit Eng. 2025; 31(4): 04025035. https://doi.org/10.1061/JAEIED.AEENG-2024
[2] Etheridge D, Ford B. Natural ventilation of tall buildings – options and limitations. In: Proceedings of the CTBUH 8th World Congress: Tall and Green – Typology for a Sustainable Urban Future; 2008; Dubai. Council on Tall Buildings and Urban Habitat; 2008.
[3] Simmonds P, Zhu R. Stack effect guidelines for tall, mega tall and super tall buildings. Int J High-Rise Build. 2013; 2(4): 323-30.
[4] Cho JS. A study of form composition and efficiency in high-rise office buildings. J Archit Inst Korea. 2007; 23(6): 33-40.
[5] Oesterle E, Lieb RD, Lutz M, Heusler W. Double skin facades: integrated planning. Munich: Prestel Verlag; 2001.
[6] Tsou JY. Strategy on applying computational fluid dynamics for building performance evaluation. Autom Constr. 2001; 10: 327-35. https://doi.org/10.1016/S0926-5805(00)00049-2
[7] Omrani S, Garcia V, Capra B, Drogemuller R. Natural ventilation in multi-story buildings: design process and review of evaluation tools. Build Environ. 2017; 116: 182-94. https://doi.org/10.1016/j.buildenv.2017.02.012
[8] Watakabe M, Ohashi M, Okada H, Okuda Y, Kikitsu H, Ito S, et al. Comparison of wind pressure measurements on tower-like structures obtained from full-scale observation, wind tunnel tests, and CFD technology. J Wind Eng Ind Aerodyn. 2002; 90: 1817-829. https://doi.org/10.1016/S0167-6105(02)00290-8
[9] Van Hooff T, Blocken B, Aanen L, Bronsema B. A venturi-shaped roof for wind-induced natural ventilation of buildings: wind tunnel and CFD evaluation of different design configurations. Build Environ. 2011; 46: 1797-807. https://doi.org/10.1016/j.buildenv.2011.02.009
[10] De Gracia A, Castell A, Navarro L, Oro E, Cabeza LF. Numerical modelling of ventilated facades: a review. Renew Sust Energ Rev. 2013; 22: 539-49. https://doi.org/10.1016/j.rser.2013.02.029
[11] Hansen RJ, Reed JW, Vanmarcke EH. Human response to wind-induced motion of buildings. J Struct Div ASCE. 1973; 99(ST7):1589-605. https://doi.org/10.1061/JSDEAG.0003564
[12] Burton MD, Kwok KCS, Abdelrazaq A. Wind-induced motion of tall buildings: Designing for occupant comfort. Int J High-Rise Build. 2015; 4(1): 1-8. https://doi.org/10.21022/IJHRB.2015.4.1.001
[13] Fisk WJ, Black D, Brunner G. Changing ventilation rates in U.S. offices: Implications for health, work performance, energy, and associated economics. Build Environ. 2012; 47: 368-72. https://doi.org/10.1016/j.buildenv.2011.07.001
[14] Nowak D, Werner J, Parsons Q, Johnson T, Mark A, Edelvik F. Optimisation of city structures with respect to high wind speeds using U-Net models. Eng Appl Artif Intell. 2024; 135: 108812. https://doi.org/10.1016/j.engappai.2024.108812
[15] Gür M, Karadağ I. Machine learning for pedestrian-level wind comfort analysis. Buildings. 2024;14(6):1845. https://doi.org/10.3390/buildings14061845.
[16] Bohm M. Building performance simulation for sensemaking in architectural pedagogy. Buildings Cities. 2025; 6(1): 450-65. https://doi.org/10.5334/bc.554
[17] Ma Z, Cooper P, Daly D, Ledo L. A review of the applications of artificial intelligence and big data to buildings for energy-efficiency and a comfortable indoor living environment. Energy Build. 2019; 202: 109383. https://doi.org/10.1016/j.enbuild.2019.109383
[18] Filippova E, Hedayat S, Ziarati T, Manganelli M. Artificial intelligence and digital twins for bioclimatic building design: innovations in sustainability and efficiency. Energies. 2025; 18: 5230. https://doi.org/10.3390/en18195230
[19] Sourav, Ali R. LAPQ-BDTH: Lightweight authentication for postquantum secure blockchain in digital twin healthcare. IEEE Internet Things J. 2026; 13(1): 1144-55. https://doi.org/10.1109/JIOT.2025.3629806
[20] Fanger PO, Pedersen CJK. Discomfort due to air velocities in spaces. In: Proceedings of the meeting of commission B1, B2, E1 of the international institute of refrigeration Vol 4. Paris; 1977.
[21] Toftum J. Air movement—good or bad? Indoor Air. 2004; 14(Suppl 7): 40-5. https://doi.org/10.1111/j.1600-0668.2004.00271
[22] Zhou G, Melikov AK. Equivalent frequency—A new parameter for description of frequency characteristics of airflow fluctuations. In: Proceedings of RoomVent 2002: 8th International Conference on Air Distribution in Rooms; 2002 Sep 8–11; Copenhagen, Denmark. p. 357-60.
[23] Lawson TV. The wind content of the built environment. J Wind Eng Ind Aerodyn. 1978; b3(2–3): b93-105. https://doi.org/10.1016/0167-6105(78)90002-8.
[24] Tamura K, Matsumoto S, Tseng YH, Kobayashi T, Miwa J, Miyazawa K, et al. Physiological and subjective comfort evaluation under different airflow directions in a cooling environment. PLoS One. 2021; 16(4): e0249235. https://doi.org/10.1371/journal.pone.0249235
[25] Tamura K, Matsumoto S, Tseng YH, Kobayashi T, Miwa J, Miyazawa K, et al. Physiological comfort evaluation under different airflow directions in a heating environment. J Physiol Anthropol. 2022; 41: 16. https://doi.org/10.1186/s40101-022-00289-x
[26] Lamb S, Kwok KCS, Walton D. Occupant comfort in wind-excited tall buildings: Motion sickness, compensatory behaviours and complaint. J Wind Eng Ind Aerodyn. 2013; 119: 1-12. https://doi.org/10.1016/j.jweia.2013.05.004
[27] Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J. Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems. 2013; 26: 3111-9.
[28] Larkin JH, Simon HA. Why a diagram is (sometimes) worth ten thousand words. Cogn Sci. 1987; 11(1): 65-100. https://doi.org/10.1016/S0364-0213(87)80026-5
[29] Kim Y, Elnimeiri MM, Clark RJ. The impact of double-skin façades on indoor airflow in naturally ventilated tall office buildings. Int J High-Rise Build. 2023; 12(2): 129-36. https://doi.org/10.21022/ijhrb.2023.12.2.129
[30] Bengio Y, Courville A, Vincent P. Representation learning: A review and new perspectives. IEEE Trans Pattern Anal Mach Intell. 2013; 35(8): 1798-828. https://doi.org/10.1109/TPAMI.2013.50
[31] Goodfellow I, Bengio Y, Courville A. Deep learning. Cambridge (MA): MIT Press; 2016.
[32] Auliciems A, Szokolay SV. Thermal comfort. Brisbane: Department of Architecture, University of Queensland; 1997.
[33] Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. PyTorch: An imperative style, high-performance deep learning library. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS). Red Hook (NY): Curran Associates; 2019. p. 721-32.
[34] Kingma DP, Ba J. Adam: A method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (ICLR); 2015.
[35] Yeh AGO, Yuen B. Tall building living in high density cities: a comparison of Hong Kong and Singapore. In: Yuen B, Yeh AGO, Eds. High-Rise Building Living in Asian Cities. London: Springer; 2011. p. 9-23.
[36] Ng CF. Living and working in tall buildings: satisfaction and perceived benefits and concerns of occupants. Front Built Environ. 2017; 3: 70. https://doi.org/10.3389/fbuil.2017.00070
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2025 Yohan Kim, Chang He
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All the published articles are licensed under the terms of the Creative Commons Attribution Non-Commercial License (CC BY-NC 4.0) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.
