مهتاب مجيدي

Social sustainability in architecture is often overlooked an‎d holds a secondary position compared to environmental an‎d economic dimensions. This research aims to bridge these aspects by introducing visual comfort as a connecting link between them. In this context, the combination of daylight access an‎d view quality is examined as key indicators of visual comfort. In this study, an integrated framework based on artificial intelligence an‎d environmental simulation was developed to enable simultaneous eva‎luation an‎d optimization of daylight an‎d view performance at the neighborhood scale. The case study was a residential complex in Tehran, where daylight metrics (DA, UDI, ASE, GA) an‎d the View Quality Index (VQI) were calculated through parametric simulations. The resulting dataset was used to train an Artificial Neural Network (ANN) model, which was then extended to odd-numbered floors using interpolation an‎d extrapolation techniques. Results showed that the ANN model achieved high accuracy in predicting daylight an‎d view metrics. Sensitivity analysis revealed that the Window-to-Wall Ratio (WWR) is the most influential design parameter, a multi-objective optimization was performed, identifying balanced design solutions that achieve an appropriate trade-off between daylight, view quality, an‎d glare control. Optimal patterns varied according to orientation an‎d floor level, an‎d recommended design ranges for window parameters were proposed. The innovation of this research lies in the development of an integrated framework that, by combining artificial intelligence an‎d visual comfort as a bridge between social an‎d environmental sustainability, enables fast an‎d accurate analysis in the early stages of design while significantly reducing computational time an‎d resources.

آسايش بصري , پايداري اجتماعي , شبكه عصبي مصنوعي , بهينه‌سازي طراحي , مقياس همسايگي

Visual comfort , Social sustainability , Artificial neural network , Multi-objective optimization , Neighborhood scale

Mahtab Majidi

Dr. Mohammadali Khanmohammadi, Dr. Neda Sahraghard Monfared