Artificial Intelligence-Driven Adaptive Facade Systems in High-Rise Buildings: A Study on Integrating Machine Learning With Real-Time Environmental Data to Optimize Energy Efficiency

Abstract

Abstract. This article investigates the integration of artificial intelligence (AI) into adaptive façade systems in high-rise buildings to improve energy efficiency through real-time reactivity with external conditions. Three façade systems—static, preprogrammed, and AI-powered adaptive façade systems—are modeled and evaluated using Rhino and Grasshopper, Ladybug Tools, OpenStudio, a full simulation environment, and algorithmic optimization techniques. The study assesses the potential of AI-driven façades to outperform both static and preprogrammed adaptive systems under various climatic scenarios by integrating a machine learning (ML) model trained using the extreme gradient boosting (XGBoost) algorithm on contextual cross-validated environmental and building performance data. The findings show that AI-enhanced systems provide notable gains in energy efficiency and reactivity, especially under harsh weather.