Application of Artificial Intelligence on Design Strategies to Optimize Urban Wind Energy
Bibliographic record
Abstract
Maximizing urban wind energy capture constitutes a step towards self-sufficient buildings. Optimizing urban wind power requires knowledge of the environmental and building parameters modifying energy capture and tools for predicting urban wind behaviors. This thesis main objective is to build a database to develop artificial intelligence (AI) programs to evaluate different design strategies and optimize urban wind energy. The database includes experimental wind tunnel velocities and turbulence intensities for terrain roughness, channeling effect, typical building shapes and several city configurations for several turbine locations. Wind velocities and turbulence intensities measured at the street-level and rooftop turbines on rectangular, U-shaped, and L-shaped buildings are further investigated with literature CFD results. Through the different combinations of experimental results and literature, a total of over 150 cases are added to the database. A decisional flow chart is developed using the results database and served as a results summary and an aid for programming the artificial intelligence (AI) networks. The elaborated database is implemented in an expert system and an artificial neural network. The AI programs are tested with city configurations models and a real case study, René-Lévesque Boulevard in downtown Montreal. Comparing the testing set to the actual experimental values, the data expert system predicts the modification in wind velocities with 68% - 98%accuracy. The feedforward artificial neural network developed is slightly more accurate than the expert system, showing success rates from 76% to 99%. Thus, AI tools and the decisional flow chart approach may be used for a preliminary assessment of the different design strategies power capture in urban environment.
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 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 | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".