Investigating Surrogate-based Models for Holistic Building Performance Assessment and Retrofit Solutions
Bibliographic record
Abstract
Existing commercial buildings in Québec are responsible for a major share of GHG emissions within the local building sector, yet limited progress has been achieved in their operational transformations over the past decades. Building retrofit is recognized as a key approach to improving energy efficiency while considering the intertwining economic and environmental effects of the applied retrofit measures. Balancing these objectives transforms the problem into a high-dimensional, multi-objective, and challenging task requiring iterative simulations. When conventional physics-based approaches are used, such analyses become computationally prohibitive, with the challenge further intensifying when analyzing multiple buildings or extending the scope to future building performance. This thesis addresses the highlighted challenge by developing surrogate models that allow the investigation of high-dimensional retrofit analyses. The study establishes a holistic building retrofit framework for post-industrialized buildings within the Montréal region to rigorously identify feasible retrofit measures specific to the studied building typology. It further develops robust surrogate models for energy consumption, embodied carbon, and investment costs that aid in decision-making across a wide array of measures. The methodology is further extended to integrate future building performance through feature extraction methods. Similarly, the study extends the generalizability of the surrogates to a multi-building analysis using a bottom-up approach, which integrates additional training data samples. Given the prevalence of data scarcity in commercial buildings, the methodology integrates building archetypes while identifying the modelling approach that accurately represents the studied building typology. The findings demonstrate the robustness of the surrogate-based approach in building retrofit analyses, highlighting a significant improvement in computational efficiency. This thesis introduces a comprehensive methodological framework that advances building performance assessment using surrogate-based methods, identifying their limitations and effectiveness in the building retrofit research domain.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".