A Machine Learning Framework for Fire Risk Prediction With Response and Proximity Insights
Bibliographic record
Abstract
Advances in artificial intelligence (AI) and machine learning (ML) have significantly enhanced fire risk assessment by enabling predictive analytics, real-time decision support, and optimized emergency response. Accurate fire risk assessments are crucial for prioritizing high-risk zones and optimizing resource deployment to minimize damage and enhance safety. In this work, we introduce novel fire risk models and propose a comprehensive ML-based framework for fire risk prediction that supports data-driven decision-making for fire and emergency response services. Our models incorporate response performance and service proximity to assess the impact of incidents more effectively within a city. The proposed framework provides an end-to-end ML pipeline that integrates diverse data sources to construct a dataset, compute risk scores, analyze key features, and formulate fire risk prediction as a regression problem. Additionally, it evaluates multiple regression models to analyze risk variations at both the incident and neighborhood levels. Experimental results demonstrate that our proposed models achieve a high degree of alignment between predicted and actual risk scores with minimal error. This framework captures valuable spatial risk patterns and can be used as a reliable tool for fire risk assessment, resource allocation, response strategy improvement, and urban safety planning.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".