Beyond Forecasting: Discovering Hidden Weather Regimes using Multivariate Clustering
Bibliographic record
Abstract
Knowledge of urban weather regimes is critical for environmental planning, disaster preparedness, and climatic monitoring in metropolitan areas. This study presents an evidence-based framework for detecting and characterizing such regimes utilising daily meteorological data from 43 cities across the United States, Canada, and Israel, spanning February 2012 to October 2017. Key variables include air pressure, wind speed, temperature, and relative humidity. The data were preprocessed through aggregation, missing value imputation, outlier treatment, and standardization to ensure quality and consistency. Principal Component Analysis (PCA) was applied for dimensionality reduction to extract dominant patterns, followed by clustering using an enhanced Canopy-KMeans algorithm with minimum variance initialization, optimal k selection via the Elbow Method, and computational efficiency achieved through the triangle inequality. Temporal persistence filtering ensured that identified regimes represent physically meaningful and stable atmospheric states. Five distinct regimes were classified: Hot–Humid Calm, Mild–Dry Transitional, Mild–Windy Transitional, Cold–Humid Unstable, and Hot–Dry Windy. Cluster centroids and intra-cluster variability provide quantitative descriptions of each regime’s environmental characteristics. Validation using the Davies-Bouldin Index, Silhouette coefficient, Calinski-Harabasz Index, and Adjusted Rand Index confirms that k = 5 yields the most stable and interpretable solution. The proposed framework offers a robust foundation for urban weather characterization, with potential applications in climate assessment and risk mitigation.
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 | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| 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".