Predicting thermal environment metrics using surrogates of physics-based building models
Bibliographic record
Abstract
Abstract Practitioners increasingly require pre-design modeling capabilities to guide efforts in housing renovations, which can be expensive and time-consuming. In parallel, researchers have advanced building surrogate modeling techniques to reduce simulation time, but little work has been done on models predicting indoor environmental conditions at sub-annual resolutions to support passive design and performance. This work develops the capability to simulate indoor thermal conditions at much higher speeds than traditional workflows. This is achieved through a flexible methodology that transforms physics-based building performance simulation (BPS) models into reduced order surrogate models, utilizing machine learning (ML) techniques as well as dataset generation through parallel computing. The surrogate outputs predict thermal environment measures, such as operative temperature, air temperature, and standard effective temperature. This study applies the workflow to a residential single-family archetype in Canada, achieving accurate predictions with errors lower than 5% CV(RMSE), and very little over- or under-estimation (NMBE lower than 0.06%) at speeds more than six times faster than typical surrogate modelling workflows. This work is significant because it leverages surrogate modeling techniques to predict indoor thermal conditions, supporting design workflows that highlight thermal autonomy, i.e., a building’s ability to passively maintain comfortable conditions for occupants.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".