Dataset for "A Probabilistic Framework for Spatio-Temporal Social Vulnerability Assessment to Flood Hazards in Canada using Bayesian Machine Learning"
Bibliographic record
Abstract
This dataset provides the foundational geospatial and socioeconomic data used in the manuscript "A probabilistic framework for spatio-temporal social vulnerability assessment to flood hazards in Canada using Bayesian machine learning" (Chakraborty et al., 2025), accepted and published in the Springer Nature "Journal of Geovisualization and Spatial Analysis" (DOI: 10.1007/s41651-025-00247-y). It offers a comprehensive suite of indicators designed to quantify social vulnerability through advanced computational methods, including Bayesian machine learning (ML), mutual information regression (MIR), and Monte Carlo simulations. This dataset ensures maximum transferability of the research and allows for the precise reproducibility of empirical results. Users are responsible for verifying the accuracy and applicability of the data for their specific needs. Redistribution or commercial use of the data is subject to licensing restrictions from original data providers. Cite appropriately when using this dataset in other publications or presentations. Key Components: Geospatial Layers: Shapefiles (.shp) containing administrative boundaries and spatial attributes. Socioeconomic & Demographic Indicators: Processed variables from Statistics Canada, including income, housing, and education metrics. Racial/Ethnic Variables: Specific data layers used to assess distributive environmental justice and disproportionate risk. Documentation: A detailed data dictionary defining all variables and attributes. Research Application This dataset is curated for researchers and practitioners working in: Dynamic Social Vulnerability Analysis: Monitoring how vulnerability shifts over time and space. Probabilistic Risk Assessment: Incorporating uncertainty into flood risk modeling. Environmental Justice: Evaluating the distributive impacts of natural hazards on marginalized populations. Emergency Management: Supporting evidence-based, proactive disaster risk reduction strategies in Canada. Technical Details Software Requirements: Data processing was conducted using ArcGIS Pro and Python. Source Attribution: Census data are obtained from open-source Statistics Canada products; Canada flood hazard data are copyrighted by JBA Risk Management; and residential address point data are copyrighted by the DMTI CanMap Suite. Contact Information For inquiries regarding the methodology or data application, please contact the corresponding author: Dr. Liton Chakraborty University of Waterloo: liton.chakraborty@uwaterloo.ca, or York University: litonch@yorku.ca
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.006 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.004 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.042 | 0.017 |
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".