Exploring machine learning algorithms for automating complex processes in building and landscape architecture
Year: 2024
Type: article
Abstract: This research examines the transformative impact of machine learning algorithms in building and landscape architecture automation. Through analysis of advanced deep learning and reinforcement learning systems, we demonstrate how these technologies enhance design optimization, environmental analysis, and sustainable landscape planning. Our findings, based on case studies from Dubai and Barcelona, reveal significant improvements in building performance and resource management through machine learning automation. The Dubai International Financial Centre implementation demonstrated substantial energy consumption reduction through automated HVAC optimization while maintaining optimal comfort levels. At the Barcelona Botanical Gardens, the intelligent landscape irrigation system achieved 40% water conservation compared to traditional methods. However, the research identifies critical challenges in data quality, algorithm reliability, and system integration. The successful implementation of architectural automation requires careful balance between computational capabilities and human expertise. Our analysis provides a framework for developing robust automation systems that maintain essential human oversight while leveraging machine learning's analytical power. This study concludes that while machine learning significantly enhances architectural automation, its effective implementation depends on careful consideration of technical limitations and the maintenance of human judgment in critical decision-making processes.
Authors: Temitope Sunday Adeusi, Onah Louis Kachiside, Ibrahim Musa Oyewole
Institutions: Joseph Ayo Babalola University, University of Nigeria
Language: English
Subfield: Architecture
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4405954201