Search

This paper explores the applications and impacts of artificial intelligence (AI) in building envelopes and interior space design. The relevant literature was searched using databases such as Science Direct, Web of Science, Scopus, and CNKI, and 89 studies were selected for analysis based on the PRISMA protocol. This paper first analyzes the role of AI in transforming architectural design methods, particularly its different roles in the auxiliary, collaborative, and leading design processes. It then discusses AI's applications in the energy-efficient renovation of building envelopes, smart façade design for cold climate buildings, and thermal imaging detection. Furthermore, this paper summarizes AI-based interior space environment design methods, covering the current state of research, applications, impacts, and challenges both domestically and internationally. Finally, this paper looks ahead to the broad prospects for AI technology in the architecture and interior design fields while addressing the challenges related to the integration of personalized design and environmental sustainability concepts. [ABSTRACT FROM AUTHOR]

As global climate change becomes increasingly severe, low-carbon city construction has emerged as a critical strategy to address this challenge. This study explores the concept, current development status, and challenges of low-carbon cities, focusing on the progress and issues in China's low-carbon city construction. The research covers defining low-carbon cities, their background, policy impacts, and analysis of practical cases. Specifically, the research focuses on identifying the challenges faced in the development of low-carbon cities in China and proposing strategies to effectively address these obstacles. Findings suggest that difficulties, such as regional disparities, inconsistencies in policy implementation, and technological barriers, hinder progress. By synthesizing insights from previous studies, this paper proposes actionable strategies, including strengthening policy frameworks for consistent application, leveraging smart technologies for efficient energy and resource management, and fostering public engagement through targeted education. These recommendations provide a guideline for future research and practical actions, contributing to sustainable urban development and offering insights for policymakers and urban planners. [ABSTRACT FROM AUTHOR]

Featured Application: The application of Artificial Intelligence (AI) in architectural design can significantly enhance design efficiency, foster innovation, and improve the sustainability of building projects. AI-driven tools, such as parametric design and AI-assisted design methods, are already helping architects optimize layouts, reduce material waste, and create energy-efficient structures. As AI continues to evolve, its potential to streamline construction processes, provide predictive analytics for building performance, and enable smarter facility management could reshape the entire building lifecycle, making the construction industry more adaptive and resilient to future challenges. At present, Artificial Intelligence (AI) technology is developing rapidly, and the construction industry is facing three major trends: industrialization, greening, and digital intelligence. This paper explores the application of AI technology in the field of architectural design and its impact on design efficiency, with 1810 articles screened from the Science Direct, Web of Science, Scopus, and China National Knowledge Network (CNKI) search engines, 92 of which were selected for meta-analysis and review. The results show that AI has great potential in the architectural design process, including creative development, data analysis, and problem-solving. In addition, AI has other applications throughout the building lifecycle, such as predictive analytics, construction supervision, and facility maintenance. In addition, through the discussion of traditional architectural design methods and AI-driven architectural design methods, this paper summarizes the advantages and challenges of AI technology in architectural design. Finally, through case analysis, this paper believes that the future of AI in the field of construction is full of infinite possibilities; through the correct guidance and regulation of its development, it will certainly bring more innovation and progress for the construction industry. [ABSTRACT FROM AUTHOR]

The Logarithmic Mean Divisia Index (LMDI) method is widely applied in research on carbon emissions, urban energy consumption, and the building sector, and is useful for theoretical research and evaluation. The approach is especially beneficial for combating climate change and encouraging energy transitions. During the method's development, there are opportunities to develop advanced formulas to improve the accuracy of studies, as indicated by past research, that have yet to be fully explored through experimentation. This study reviews previous research on the LMDI method in the context of building carbon emissions, offering a comprehensive overview of its application. It summarizes the technical foundations, applications, and evaluations of the LMDI method and analyzes the major research trends and common calculation methods used in the past 25 years in the LMDI-related field. Moreover, it reviews the use of the LMDI in the building sector, urban energy, and carbon emissions and discusses other methods, such as the Generalized Divisia Index Method (GDIM), Decision Making Trial and Evaluation Laboratory (DEMATEL), and Interpretive Structural Modeling (ISM) techniques. This study explores and compares the advantages and disadvantages of these methods and their use in the building sector to the LMDI. Finally, this paper concludes by highlighting future possibilities of the LMDI, suggesting how the LMDI can be integrated with other models for more comprehensive analysis. However, in current research, there is still a lack of an extensive study of the driving factors in low-carbon city development. The previous related studies often focused on single factors or specific domains without an interdisciplinary understanding of the interactions between factors. Moreover, traditional decomposition methods, such as the LMDI, face challenges in handling large-scale data and highly depend on data quality. Together with the estimation of kernel density and spatial correlation analysis, the enhanced LMDI method overcomes these drawbacks by offering a more comprehensive review of the drivers of energy usage and carbon emissions. Integrating machine learning and big data technologies can enhance data-processing capabilities and analytical accuracy, offering scientific policy recommendations and practical tools for low-carbon city development. Through particular case studies, this paper indicates the effectiveness of these approaches and proposes measures that include optimizing building design, enhancing energy efficiency, and refining energy-management procedures. These efforts aim to promote smart cities and achieve sustainable development goals. [ABSTRACT FROM AUTHOR]