Inverse surrogate modelling to determine thermal characteristics of buildings
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Planning building energy retrofits effectively requires knowledge of the current state of the building envelope, which is often lacking in practice. This study examines the usage of an Inverse Surrogate Model (ISM) for the purposes of determining various building parameters, such as the wall insulation conductivity and infiltration flow rate, to assist in retrofit planning. A typical Surrogate Model (SM) is a machine learning model trained on detailed simulation inputs to predict outputs, so that it can be used as a fast but approximate substitute for the detailed model. An Inverse Surrogate Model (ISM) does the opposite by instead predicting which inputs were used in the detailed model (e.g. wall insulation thickness) to produce a specific set of outputs (e.g. a temperature time series). This study develops a convolutional neural network (CNN) to act as the ISM, as these have been shown to work well with time-domain problems.An EnergyPlus simulation model of an existing building was developed and various parameters were randomly varied to produce a training dataset consisting of parameter values and associated room temperature time series. The CNN was trained using this dataset to predict parameter values when given a time series as input. The ISM performance is assessed with a variety of common error metrics including the Coefficient of Determination (R2), Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). Results indicated strong performance with the majority of parameters.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it