Investigating Machine Learning Algorithms within the Conceptual Design Phase, Analyzing Building Energy Consumption and Construction Phase

The application of computation in design domains has improved design process methodologies from CAD to BIM, leading to more efficient approaches to problem-solving and decision-making. In particular, machine learning algorithms are being used in the design process because of their efficient learning, analyzing, and prediction capabilities. The present study leverages machine learning in the context of built environments and explores the possible implementation of diverse ML methodologies throughout the conceptual design stage and building performance analysis. This article investigates the latest developments in machine learning and their applications to built environments and architectural design… The study also looks at new issues in the built environment and how machine learning ideas may be applied in the future to address them. The use of generative adversarial networks (GAN), convolutional neural networks (CNN), and deep neural networks (DNN) in the creation of floor plans, enhancement of energy efficiency, capturing architectural styles, defect assessment, and other applications is examined in this research study. Its ramifications are appropriate for reaching sustainable solutions for issues like energy use, preserving cultural heritage, etc. in the built environment. This research implies that these intelligent algorithms will enable the emergence of interdisciplinary strategies to evolve to address existing problems and find efficient solutions.