Rapid indoor airflow prediction using a hybrid residual learning regression model
Bibliographic record
Abstract
Ventilation performance and resulting indoor airflow patterns influence indoor air quality, thermal comfort, and energy consumption, particularly in densely occupied spaces such as classrooms. Nonetheless, accurate airflow prediction remains a challenge. Computational Fluid Dynamics (CFD) provides detailed predictions but is computationally intensive, while machine-learning (ML) models, though faster, operate as black boxes and are limited to the geometry used for training. To address this, we propose a physics-guided ML model termed Residual Learning Regression (RLR), which integrates Multivariate Linear Regression (MLR) with Extreme Gradient Boosting (XGB) residual correction. This hybrid model was trained on 149 validated classroom CFD simulations spanning the effect of diffuser geometry, air change rate, inlet temperature, and occupancy level on airflow patterns. From the RLR, four equations were derived to predict the spatially averaged values of airflow mixing, ventilation effectiveness, temperature, and velocity at the breathing level. Further, geometry-based correction factors were introduced, extending equations’ applicability to room volumes of 25–532 m 3 . Results show that the RLR improves baseline MLR accuracy by about 10 % and achieves airflow prediction comparable to XGB, while maintaining interpretability. Independent experimental validation and uncertainty analysis showed deviations within credible bounds, confirming the model’s robustness. The developed RLR equations offer a scalable and reliable alternative to CFD and black-box ML, bridging the gap between high-fidelity modeling and rapid ventilation assessment. Importantly, its transparent structure and predictive accuracy highlight the RLR model’s potential to inform future ventilation design standards and guidelines, supporting healthier and energy-efficient buildings.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| 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".