Deep Learning-Driven Optimization of Fenestration for Daylighting in Hot-Arid Climates: A Hybrid Evolutionary Framework

Document Type : Original Article

Authors

1 Department of Urbanism, Tourism, Architecture and Research Center, Isf.C., Islamic Azad University, Isfahan, Iran.

2 Department of Architecture, Tourism, Architecture and Research Center, Isf.C., Islamic Azad University, Isfahan, Iran.

Abstract

This study articulates a pioneering, integrated methodology for the optimization of fenestration and spatial configuration in residential living rooms, tailored specifically to the exigencies of Isfahan’s hot-arid climate. The overarching objective is the maximization of daylighting performance through the simultaneous evaluation of three pivotal climate-based metrics: Spatial Daylight Autonomy (sDA), Annual Sunlight Exposure (ASE), and Useful Daylight Illuminance (UDI). Distinctively, this research synergizes a Deep Learning (DL) predictive model with a genetic algorithm-based multi-objective optimization framework (Galapagos), transcending the limitations of traditional static modeling techniques. The deployed feedforward neural network exhibited exemplary predictive fidelity, yielding R² coefficients of 0.97 for UDI and ASE, and a perfect 1.00 for sDA. Subsequent interpretability analyses underscored the critical impact of room depth and Window-to-Wall Ratio (WWR) on luminous performance. The optimization protocol culminated in a definitive design archetype for a south-facing volume (4m width × 5m depth), oriented at a -1-degree azimuth. This configuration, featuring a 30% WWR distributed across two vertical apertures with a 0.90m sill height and devoid of external shading, achieved an optimal equilibrium: 100% sDA, 43% ASE, and 72% UDI. Consequently, this work establishes a robust, data-driven framework for sustainable architectural practice, offering precise parametric guidelines for daylighting efficacy in challenging climatic zones.

Keywords

Main Subjects

References

Aldersoni, A. (2025). Optimizing residential energy efficiency through strategic landscaping in Hot-Arid regions. International Journal of Architectural Engineering Technology, 12, 8–29. https://doi.org/10.15377/2409-9821.2025.12.2
Bhandari, N., & Sundaram, A. M. (2019). Optimization of windows for daylighting and energy consumption for south facade in office building in hot and dry climate of India. In A. Chakrabarti & A. M. Sundaram (Eds.), Smart innovation, systems and technologies. Springer. 307–320. https://doi.org/10.1007/978-981-13-5974-3_27
Bian, Y., Zhou, Y., Yang, S., Lin, D., & Ma, Y. (2025). Using machine learning algorithm to predict lighting energy consumption of daylight-linked lighting systems from spatial daylight autonomy. Energy and Buildings, 341, 115847. https://doi.org/10.1016/j.enbuild.2025.115847
Carlucci, S., Causone, F., De Rosa, F., & Pagliano, L. (2015). A review of indices for assessing visual comfort with a view to their use in optimization processes to support building integrated design. Renewable and Sustainable Energy Reviews, 47, 1016–1033.
Fadeyi, A., John, I., Uduma-Olugu, N., & Adebamowo, M. (2024). Optimizing residential building orientation for sustainable daylighting in the tropics: A case study in Lagos, Nigeria. International Journal of Scientific Research and Management (IJSRM), 12(3), 5963-5971. https://doi.org/10.18535/ijsrm/v12i03.em02
Fahmy, M. K., & Elsoudany, M. (2023). Parametric Mashrabiya as a shading system for optimized daylighting in Egypt. Engineering Research Journal, 177(0), 212-230. https://doi.org/10.21608/erj.2023.289551
Glazer, J., Megan, M., Wuethrich, F., Li, L. Y., Walther, S., Mittal, V., & Shankman, S. (2023). Brighten your day: exploring daily associations between natural daily light exposure and positive mood. Biological Psychiatry, 93(9), S63. https://doi.org/10.1016/j.biopsych.2023.02.171
Goldberg, X. (2025). Natural daylight exposure improves mood. Nature Reviews Psychology, 4(7), 437. https://doi.org/10.1038/s44159-025-00470-w
He, Q., Li, Z., Gao, W., Chen, H., Wu, X., Cheng, X., & Lin, B. (2021). Predictive models for daylight performance of general floorplans based on CNN and GAN: A proof-of-concept study. Building and Environment, 206, 108346. https://doi.org/10.1016/j.buildenv.2021.108346
Javanmard, Z., Davtalab, J., Nikpour, M., & Sivandipour, A. (2024). Integrating machine learning and parametric design for energy-efficient building cladding systems in arid climates: Sport Hall in Kerman. Journal of Building Engineering, 97, 110693. https://doi.org/10.1016/j.jobe.2024.110693
Le-Thanh, L., Nguyen-Thi-Viet, H., Lee, J., & Nguyen-Xuan, H. (2022). Machine learning-based real-time daylight analysis in buildings. Journal of Building Engineering, 52, 104374. https://doi.org/10.1016/j.jobe.2022.104374
Li, L. (2024). Research on daylighting optimization of building space layout based on parametric design. Sustainable Buildings, 7, 3. https://doi.org/10.1051/sbuild/2024003
Li, S., Li, D. H., Chen, W., Lou, S., & Tsang, E. K. (2023). Simple mathematical models to link climate-based daylight metrics with daylight factor metrics and daylighting design implications. Heliyon, 9(5), e15786. https://doi.org/10.1016/j.heliyon.2023.e15786
Li, X., Yuan, Y., Liu, G., Han, Z., & Stouffs, R. (2024). A predictive model for daylight performance based on multimodal generative adversarial networks at the early design stage. Energy and Buildings, 305, 113876. https://doi.org/10.1016/j.enbuild.2023.113876
Liu, L., Sun, C., Liu, Y., Leng, H., & Yang, Y. (2024). Optimized design research on daylighting performance of cold land buildings based on improved neural network. Applied Mathematics and Nonlinear Sciences, 9(1). https://doi.org/10.2478/amns-2024-0730
Liu, Q., Chen, Y., Liu, Y., Lei, Y., Wang, Y., & Hu, P. (2023). A review and guide on selecting and optimizing machine learning algorithms for daylight prediction. Building and Environment, 244, 110822. https://doi.org/10.1016/j.buildenv.2023.110822
Liu, Y., Colburn, A., & Inanici, M. (2020). Deep neural network approach for annual luminance simulations. Journal of Building Performance Simulation, 13(5), 532–554. https://doi.org/10.1080/19401493.2020.1803404
Luo, J., Zhuang, Z., Bian, Y., Wu, B., & Liang, G. (2024). Daylighting performance prediction model for linear layouts of teaching building clusters utilizing deep learning. Sustainable Cities and Society, 115, 105821. https://doi.org/10.1016/j.scs.2024.105821
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
Mousavi, S., Gheibi, M., Wacławek, S., Smith, N. R., Hajiaghaei-Keshteli, M., & Behzadian, K. (2023). Low-energy residential building optimization for energy and comfort enhancement in semi-arid climate conditions. Energy Conversion and Management, 291, 117264. https://doi.org.10.1016/j.enconman.2023.117264
Park, J.-D., Lee, Y.-K., & Kim, D.-W. (2015). A parametric analysis for daylighting driven design optimization of office buildings. Journal of the Architectural Institute of Korea Planning & Design, 31(9), 21-28. https://doi.org/10.5659/JAIK_PD.2015.31.9.21
Qahtan, A. M., Bahdad, A. A. S., Al-Tamimi, N., & Fadzil, S. F. S. (2024). Optimizing daylighting in lecture halls within hot-arid climates through modification of glazing systems with light-shelves: A parametric design approach. Indoor and Built Environment, 33(5), 929–956. https://doi.org/10.1177/1420326x241226651
Rodrigues, E., Fereidani, N. A., Fernandes, M. S., & Gaspar, A. R. (2024). Diminishing benefits of thermal mass in Iranian climate: Present and future scenarios. Building and Environment, 258, 111635. https://doi.org/10.1016/j.buildenv.2024.111635
Saheb, T., Dehghani, M., & Saheb, T. (2022). Artificial intelligence for sustainable energy: A contextual topic modeling and content analysis. Sustainable Computing: Informatics and Systems, 35, 100699. https://doi.org/10.1016/j.suscom.2022.100699
Siraji, M. A., Spitschan, M., Kalavally, V., & Haque, S. (2023). Light exposure behaviors predict mood, memory and sleep quality. Scientific Reports, 13(1), 12425. https://doi.org/10.1038/s41598-023-39636-y
Toutou, A., Fikry, M., & Mohamed, W. (2018). The parametric based optimization framework daylighting and energy performance in residential buildings in hot arid zone. Alexandria Engineering Journal, 57(4), 3595-3608. https://doi.org/10.1016/j.aej.2018.04.006
Tzempelikos, A. (2017). Advances on daylighting and visual comfort research. Building and Environment, 113, 1–4.
Xu, S., Chen, Y., Liu, J., Kang, J., Gao, J., Qin, Y., Tan, W., & Li, G. (2024). Comprehensive improvement of energy efficiency and indoor environmental quality for university library atrium—A multi-objective fast optimization framework. Frontiers of Architectural Research, 14(2), 449-470. https://doi.org/10.1016/j.foar.2024.08.010
Zekry, O. S., Fekry, A. A., & Hamed, R. E. D. (2024). Artificial Neural Network to predict Curvature Light Shelf design related Daylighting Optimization on Office Spaces. Journal of Daylighting, 11(2), 334-348. https://doi.org/10.15627/jd.2024.23
Journal of Design Thinking
Volume 6, Issue 2
December 2025
Pages 281-295

Files

Share

How to cite

Statistics