Multi-region models built with machine and deep learning for predicting several heat-related health outcomes
Bibliographic record
Abstract
• Daily summer mortality and morbidity predicted for general and elderly populations. • Machine/deep learning models trained with weather, regional and temporal predictors. • Deep learning performed better globally and across regions than other ML models. • Ensemble tree-based models were more sensitive to weather variables and heatwaves. • Models provided new insights on heat-related health impacts in the two populations. As a result of climate change, populations worldwide will be exposed to more heat episodes. To ensure a sustainable future, cutting-edge tools must be developed to predict the health effects of heat and limit its consequences. However, current research has mainly focused on one health outcome in a single city/region, thus providing limited knowledge to improve society's resilience to extreme heat. In this study, a machine learning (ML) framework is introduced to predict several heat-related health outcomes in multiple regions simultaneously, using the province of Quebec (Canada) as a case study. Five ML models including penalized regression, ensemble tree-based models and deep neural networks were considered and compared. Models were trained to predict these health outcomes using various meteorological, regional and temporal predictors across all regions. Our results showed that deep learning models were the most promising, with out-of-sample R 2 of >60 % for most of the studied health outcomes. However, ensemble tree-based approaches also had the best performance for some health outcomes, and were more sensitive to weather variables and to heatwaves. By introducing novel ML-based tools for predicting heat risks in several regions, this study can guide climate change adaptation and help cities and society to become more healthy, resilient and sustainable.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".