Transforming Built Environment Performance through AI-Driven and Physics-Based Simulations

Dear Colleagues,

As the built environment faces increasing demands for energy efficiency, sustainability, and occupant health and well-being, the convergence of artificial intelligence (AI), machine learning (ML), and physics-based methods provides a powerful computational toolkit for advancing performance modeling and assessment. By leveraging the strengths of AI/ML alongside the interpretability and precision of physics-based models, this approach enhances predictive accuracy, improves design processes, and streamlines operations. This Special Issue explores how these emerging technologies can be applied to optimize design, improve operational efficiency, and contribute to the development of smarter, more sustainable built environments across various scales, from individual buildings to urban environments.

Suggested Themes

The Special Issue invites contributions on a wide range of topics, including but not limited to the following:

• AI/ML and Physics-Based Simulations—hybrid models combining AI/ML with physics-based simulations for enhanced accuracy and adaptability.
• Energy Efficiency—optimizing energy consumption and building performance through AI-driven and physics-based models.
• Indoor Environmental Quality (IEQ) – assessing and optimizing design to enhance occupant comfort, health, and overall well-being.
• Model Predictive Control—AI/ML techniques for adaptive predictive control systems in dynamic building conditions.
• Reinforcement Learning—applying reinforcement learning to enhance building control systems' autonomy and intelligence.
• Occupant-Centric Control—integrating occupant behavior to optimize real-time building performance.
• Fault Detection and Diagnosis—AI/ML-driven methods for identifying faults, enhancing reliability, and reducing costs.
• Building Grid Integration—facilitating energy flexibility and sustainability through AI and physics-based simulations.
• Computer Vision—using computer vision for visual data analysis and performance monitoring in building systems.
• Natural Language Processing (NLP)—utilizing NLP to extract insights from textual data related to building performance and management.
• Large Language Models (LLMs)—harnessing LLMs to analyze and generate human-like insights from large volumes of context-aware, complex, and domain-specific textual data.
• Big Data—leveraging big data analytics to improve decision making, predictive modeling, and operational efficiency in buildings.
• Urban Building Energy Modeling (UBEM)—urban-scale modeling to optimize energy use and sustainability within and across cities.
• Lifecycle Assessment and Sustainability—employing AI and physics-based simulations to assess and enhance building sustainability throughout their lifecycle.
• Digital Twin—integrating digital twin technology for real-time monitoring and performance optimization of urban building systems.

Dr. Narjes Abbasabadi
Dr. Mehdi Ashayeri
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Architecture is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• artificial intelligence (AI)
• machine learning (ML)
• physics-based simulations
• performance modeling
• predictive accuracy
• building design optimization
• operational efficiency
• energy efficiency
• model predictive control
• occupant-centric control
• fault detection and diagnosis
• building-grid integration
• reinforcement learning
• computer vision
• natural language processing (NLP)