Leveraging large language models to enhance urban building energy modeling: A case study
Bibliographic record
Abstract
In light of ambitious carbon neutrality targets by 2025, urban building energy modeling (UBEM) has become a promising method for reducing energy consumption and evaluating retrofitting strategies in urban environment. Establishing UBEMs at a large scale, however, faces multiple challenges including limited data sources, specialized building science requirements, and complex calibration processes. These make building modeling labor-intensive, hindering its practical applications. This work presents an innovative method to address these challenges by enhancing UBEM significantly using large language models (LLMs). We explore the potential of LLMs to streamline data acquisition, preprocessing, and preliminary overview of building and energy datasets, while also translating natural language building descriptions into formal UBEM models, ultimately aiding model creation, error detection, calibration, and retrofit scenario analysis, offering a more nuanced understanding of potential energy-saving strategies. The application of LLMs in UBEM was demonstrated through a case study involving 200 low-rise residential buildings in Montreal, Canada. By integrating LLMs into the UBEM workflow, we contribute to the advancement of UBEM methodologies, potentially accelerating the adoption of energy-efficient practices in urban planning. The findings suggest that LLMs can significantly enhance the accessibility, accuracy, and interpretability of UBEMs, ultimately supporting more effective decision-making in urban energy management and carbon reduction efforts.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".