Towards Urban Heat Loss Modeling Using Building Digital Twin
Bibliographic record
Abstract
Abstract. Seventy percent of global greenhouse gas (GHG) emissions originate from urban areas, with urban heat loss contributing significantly to energy consumption (UNEP, 2020). Digital twins offer a potential solution and insight into the problem and its causes. This is a study started as an undergraduate Engineering Capstone Project with a collaborative effort between the University of New Brunswick and the National Research Council of Canada to develop a workflow to aid thermal efficiency modeling using Digital twins. This project uses the University of New Brunswick (UNB) Fredericton campus as a case study to capture UAV, nadir perspective LiDAR, Panchromatic imagery and long wave infrared (LWIR) thermal imagery. The workflow includes 4 major steps following the preprocessing: (1) creating point clouds from the LiDAR and Panchromatic sources, (2) merging point clouds using grid-based segmentation and iterative closest point algorithm (ICP), (3) classifying the point cloud using Point CNN networks aided by manual refinement, and (4) overlaying thermal data. The resulting digital twin achieved a high level of spatial alignment accuracy, with 95% of points falling on building surfaces falling within an 11 cm tolerance as assessed by quadric cloud-to-cloud distance. Semantic classification performed using Point CNN and faster R-CNN object detection identified façade features such as windows and doors with a precision of 91.8% and an F1 score of 83%. Thermal data was successfully integrated and converted to approximate temperature values, enabling further analysis of surface heat behavior and laying the groundwork for future energy modeling applications. This case study demonstrates a scalable framework for high-detail drone based digital twin development with practical relevance to urban thermal efficiency analysis.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".