AI-driven design optimization for sustainable buildings: A systematic review
Bibliographic record
Abstract
Buildings are major contributors to global carbon emissions, accounting for a substantial portion of energy consumption and environmental impact. This situation presents a critical opportunity for energy conservation through strategic interventions in both building design and operational phases . Artificial Intelligence (AI) has emerged as a transformative approach in this context, enhancing the efficiency and precision of energy management efforts. In the operational phase, AI is extensively utilized as smart controllers for Heating, Ventilation, and Air Conditioning (HVAC) systems and passive energy gains, as well as for fault detection. In the design phase, AI is pivotal as a surrogate model , enabling rapid and accurate evaluation of design options and allowing designers to optimize building performance with minimal computational resources. As the early-stage optimization is more cost-effective than post-construction modifications, design phase optimization has a great potential. Consequently, this paper examines recent advancements in surrogate-assisted design optimization for sustainable buildings, providing a comprehensive overview of the entire optimization process, from data preparation and surrogate model training to final optimization. The review categorizes studies based on experimental approaches and methodologies, identifying trends, gaps, and opportunities in the field. Notably, it highlights how modern AI techniques can incorporate previously unexplored dimensions into surrogate-assisted optimization, broadening the scope and potential of surrogate models. Therefore, this study provides guidance for future research and practical applications of AI-driven strategies in sustainable building practices.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".