Jérémie Boudreault
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jérémie Boudreault has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
Fateh Chebana
Centre Eau Terre Environnement, Institut national de la recherche scientifique
11 shared publications- Céline Campagna
Centre Eau Terre Environnement, Institut national de la recherche scientifique
5 shared publications Céline Campagna
Centre Eau Terre Environnement, Institut national de la recherche scientifique, 490 de la Couronne, Québec, QC G1K 9A9, Canada; Département de médecine sociale et préventive, Faculté de médecine, Université Laval, 1050 Avenue de la Médecine, Québec, QC G1V 0A6, Canada; Ouranos, 550 Rue Sherbrooke W., Montréal, QC H3A 1B9, Canada
4 shared publications- David Anthony Carozza
Department of Mathematics, Université du Québec À Montréal, Montreal, QC, Canada
4 shared publications - Manuel Grenier
Department of Mathematics, Université du Québec À Montréal, Montreal, QC, Canada
4 shared publications - Mathieu Boudreault
Département de Mathématiques Université du Québec à Montréal Montréal Québec Canada
4 shared publications
Latest Publications
- Open Access
- 1 November 2026
- Published by IOP Publishing in Environmental Research Communications
- Vol. 8 (11) , 115010
Mortality and morbidity associated with winter weather conditions revealed by machine learning models
Machine learning (ML) models are being increasingly used to predict the health impacts of environmental exposures. Although cold temperatures account for a larger share of the burden of disease than hot temperatures, the use of ML to assess how winter weather conditions affect mortality and morbidity remains limited. In this study, we compared five ML models to predict cases of mortality and morbidity associated with winter conditions during the coldest months of the year in five regions of the province of Quebec, Canada. ML models, including Least absolute shrinkage and selection operator (Lasso), Decision tree (DT), Random forest (RF), Light gradient boosting model (LGBM) and Multi-layer perceptron (MLP), were calibrated to predict all-cause mortality, cardiovascular and respiratory hospitalizations during November to March months, 2000–2019. Lagged weather variables (e.g. temperature, precipitation, humidity, snowfall, freezing rain) and air pollutants (O 3 , PM 2.5 , NO 2 , SO 2 and CO) at up to 21 days were considered, as well as calendar variables (day of week, holiday, month, year). Feature importance and SHapley Additive exPlanations (SHAP) were used to reveal the most important predictors. On the selected test winter years, RF and LGBM performed better than the other models across locations to predict cardiorespiratory hospitalizations. For mortality, while RF was slightly more performant in Montreal, Lasso and calendar-only models were highly competitive in the other locations. Lagged temperatures, precipitation and air pollutants were all important to predict the three health outcomes during winter, with some differences across outcomes. Calendar variables also played a major role, especially for cardiovascular hospitalizations. Public health authorities could benefit from ML models to improve their understanding of winter weather condition associated with different health outcomes. Further studies should compare more thoroughly the performance of ML and non-ML approaches, and extend this associative study to a causal framework.
- 1 November 2026
- Published by IOP Publishing in Environmental Research Communications
- Vol. 8 (11) , 115010
Open AccessMortality and morbidity associated with winter weather conditions revealed by machine learning models
Machine learning (ML) models are being increasingly used to predict the health impacts of environmental exposures. Although cold temperatures account for a larger share of the burden of disease than hot temperatures, the use of ML to assess how winter weather conditions affect mortality and morbidity remains limited. In this study, we compared five ML models to predict cases of mortality and morbidity associated with winter conditions during the coldest months of the year in five regions of the province of Quebec, Canada. ML models, including Least absolute shrinkage and selection operator (Lasso), Decision tree (DT), Random forest (RF), Light gradient boosting model (LGBM) and Multi-layer perceptron (MLP), were calibrated to predict all-cause mortality, cardiovascular and respiratory hospitalizations during November to March months, 2000–2019. Lagged weather variables (e.g. temperature, precipitation, humidity, snowfall, freezing rain) and air pollutants (O 3 , PM 2.5 , NO 2 , SO 2 and CO) at up to 21 days were considered, as well as calendar variables (day of week, holiday, month, year). Feature importance and SHapley Additive exPlanations (SHAP) were used to reveal the most important predictors. On the selected test winter years, RF and LGBM performed better than the other models across locations to predict cardiorespiratory hospitalizations. For mortality, while RF was slightly more performant in Montreal, Lasso and calendar-only models were highly competitive in the other locations. Lagged temperatures, precipitation and air pollutants were all important to predict the three health outcomes during winter, with some differences across outcomes. Calendar variables also played a major role, especially for cardiovascular hospitalizations. Public health authorities could benefit from ML models to improve their understanding of winter weather condition associated with different health outcomes. Further studies should compare more thoroughly the performance of ML and non-ML approaches, and extend this associative study to a causal framework.
- Open Access
- 21 May 2026
- Published by IOP Publishing in Environmental Research: Health
- Vol. 4 (2)
Quantifying heat-related and cold-related mortality burden in the context of the COVID-19 pandemic in Quebec, Canada (2000–2024)
Background: Suboptimal temperatures are becoming a major cause of mortality worldwide. However, the recent changes in temperature-related mortality burden due to the COVID-19 pandemic remain unclear, with only a few studies conducted in Europe and Asia reporting diverging results. Objective: This study aims to estimate the heat-related and cold-related mortality burden between 2000 and 2024 in the context of the COVID-19 pandemic in a North American context. Methods: Using data from the province of Quebec, Canada, we estimated temperature-mortality functions with Distributed Lag Non-Linear Models (DLNM) and multivariate meta-regression. Models were developed including or excluding COVID-19 deaths and years, as well as separately for the summer season (May to September), the winter season (November to March) and for the whole year. Mortality attributable to moderate, extreme and total heat and cold was calculated using the different models. Results: The total heat-related burden was estimated at 375 and 550 deaths per year using respectively the summer and the annual models. A non-significant reduction of ~100 heat-related deaths per year was noted when including COVID-19 years in the analysis compared to the pre-COVID-19 period. The cold-related burden was estimated at 850 and 4000 deaths per year using respectively the winter and the annual model. The cold burden was highly sensitive to the studied months and to models' parameters. Excluding COVID-19 deaths decreased the cold-related mortality burden. Discussion: These new results can help health authorities improve their temperature surveillance through a better understanding of the recent shifts due to the COVID-19 period. Heat surveillance should focus on both moderate and extreme hot temperatures, each representing half of the heat-related mortality burden, while cold surveillance should target moderate cold temperatures (i.e., 0º to -20ºC) that accounted for >90% of the cold burden.
- 21 May 2026
- Published by IOP Publishing in Environmental Research: Health
- Vol. 4 (2)
Open AccessQuantifying heat-related and cold-related mortality burden in the context of the COVID-19 pandemic in Quebec, Canada (2000–2024)
Background: Suboptimal temperatures are becoming a major cause of mortality worldwide. However, the recent changes in temperature-related mortality burden due to the COVID-19 pandemic remain unclear, with only a few studies conducted in Europe and Asia reporting diverging results. Objective: This study aims to estimate the heat-related and cold-related mortality burden between 2000 and 2024 in the context of the COVID-19 pandemic in a North American context. Methods: Using data from the province of Quebec, Canada, we estimated temperature-mortality functions with Distributed Lag Non-Linear Models (DLNM) and multivariate meta-regression. Models were developed including or excluding COVID-19 deaths and years, as well as separately for the summer season (May to September), the winter season (November to March) and for the whole year. Mortality attributable to moderate, extreme and total heat and cold was calculated using the different models. Results: The total heat-related burden was estimated at 375 and 550 deaths per year using respectively the summer and the annual models. A non-significant reduction of ~100 heat-related deaths per year was noted when including COVID-19 years in the analysis compared to the pre-COVID-19 period. The cold-related burden was estimated at 850 and 4000 deaths per year using respectively the winter and the annual model. The cold burden was highly sensitive to the studied months and to models' parameters. Excluding COVID-19 deaths decreased the cold-related mortality burden. Discussion: These new results can help health authorities improve their temperature surveillance through a better understanding of the recent shifts due to the COVID-19 period. Heat surveillance should focus on both moderate and extreme hot temperatures, each representing half of the heat-related mortality burden, while cold surveillance should target moderate cold temperatures (i.e., 0º to -20ºC) that accounted for >90% of the cold burden.
- Open Access
- 25 November 2025
- Published by Elsevier in Environment International
- Vol. 206, 109965
Machine learning for modelling the health impacts of extreme heat: A comprehensive literature review
- 25 November 2025
- Published by Elsevier in Environment International
- Vol. 206, 109965
Open AccessMachine learning for modelling the health impacts of extreme heat: A comprehensive literature review
- Open Access
- 11 June 2025
- Published by Elsevier in EBioMedicine
- Vol. 117, 105788
Exploring the relationship between medications and heat-related community deaths during the 2021 heat dome: a hybrid approach using machine learning
- 11 June 2025
- Published by Elsevier in EBioMedicine
- Vol. 117, 105788
Open AccessExploring the relationship between medications and heat-related community deaths during the 2021 heat dome: a hybrid approach using machine learning
- Open Access
- 13 December 2024
- Published by Elsevier in Science of The Total Environment
- Vol. 958, 178022
Projecting the overall heat-related health burden and associated economic costs in a climate change context in Quebec, Canada
- 13 December 2024
- Published by Elsevier in Science of The Total Environment
- Vol. 958, 178022
Open AccessProjecting the overall heat-related health burden and associated economic costs in a climate change context in Quebec, Canada
- Open Access
- 10 September 2024
- Published by Elsevier in Sustainable Cities and Society
- Vol. 115
Multi-region models built with machine and deep learning for predicting several heat-related health outcomes
- 10 September 2024
- Published by Elsevier in Sustainable Cities and Society
- Vol. 115
Open AccessMulti-region models built with machine and deep learning for predicting several heat-related health outcomes
- Open Access
- 26 July 2024
- Published by Copernicus GmbH in Natural Hazards and Earth System Sciences
- Vol. 24 (7) , 2577-2595
Flood occurrence and impact models for socioeconomic applications over Canada and the United States
Large-scale socioeconomic studies of the impacts of floods are difficult and costly for countries such as Canada and the United States due to the large number of rivers and size of watersheds. Such studies are however very important for analyzing spatial patterns and temporal trends to inform large-scale flood risk management decisions and policies. In this paper, we present different flood occurrence and impact models based upon statistical and machine learning methods of over 31 000 watersheds spread across Canada and the US. The models can be quickly calibrated and thereby easily run predictions over thousands of scenarios in a matter of minutes. As applications of the models, we present the geographical distribution of the modelled average annual number of people displaced due to flooding in Canada and the US, as well as various scenario analyses. We find for example that an increase of 10 % in average precipitation yields an increase in the displaced population of 18 % in Canada and 14 % in the US. The model can therefore be used by a broad range of end users ranging from climate scientists to economists who seek to translate climate and socioeconomic scenarios into flood probabilities and impacts measured in terms of the displaced population.
- 26 July 2024
- Published by Copernicus GmbH in Natural Hazards and Earth System Sciences
- Vol. 24 (7) , 2577-2595
Open AccessFlood occurrence and impact models for socioeconomic applications over Canada and the United States
Large-scale socioeconomic studies of the impacts of floods are difficult and costly for countries such as Canada and the United States due to the large number of rivers and size of watersheds. Such studies are however very important for analyzing spatial patterns and temporal trends to inform large-scale flood risk management decisions and policies. In this paper, we present different flood occurrence and impact models based upon statistical and machine learning methods of over 31 000 watersheds spread across Canada and the US. The models can be quickly calibrated and thereby easily run predictions over thousands of scenarios in a matter of minutes. As applications of the models, we present the geographical distribution of the modelled average annual number of people displaced due to flooding in Canada and the US, as well as various scenario analyses. We find for example that an increase of 10 % in average precipitation yields an increase in the displaced population of 18 % in Canada and 14 % in the US. The model can therefore be used by a broad range of end users ranging from climate scientists to economists who seek to translate climate and socioeconomic scenarios into flood probabilities and impacts measured in terms of the displaced population.
- Open Access
- 5 June 2024
- Published by Elsevier in Environmental Research
- Vol. 257, 119347
Estimating the heat-related mortality and morbidity burden in the province of Quebec, Canada
- 5 June 2024
- Published by Elsevier in Environmental Research
- Vol. 257, 119347
Open AccessEstimating the heat-related mortality and morbidity burden in the province of Quebec, Canada
- Open Access
- 25 March 2024
- Published by Copernicus GmbH
- Vol. 2024, 1
Reply on RC2
Large-scale socioeconomic studies of the impacts of floods are difficult and costly for countries such as Canada and the United States due to the large number of rivers and size of watersheds. Such studies are however very important to analyze spatial patterns and temporal trends to inform large-scale flood risk management decisions and policies. In this paper, we present different flood occurrence and impact models based upon statistical and machine learning methods over 31,000 watersheds spread across Canada and the US. The models can be quickly calibrated and thereby easily run predictions over thousands of scenarios in a matter of minutes. As applications of the models, we present the geographical distribution of the modelled average annual number of people displaced due to flooding in Canada and the US, as well as various scenario analyses. We find for example that an increase of 10 % in average precipitation yields an increase of population displaced of 18 % in Canada and 14 % in the U.S. The model can therefore be used by a broad range of end-users ranging from climate scientists to economists who seek to translate climate and socioeconomic scenarios into flood probabilities and impacts measured in terms of population displaced.
- 25 March 2024
- Published by Copernicus GmbH
- Vol. 2024, 1
Open AccessReply on RC2
Large-scale socioeconomic studies of the impacts of floods are difficult and costly for countries such as Canada and the United States due to the large number of rivers and size of watersheds. Such studies are however very important to analyze spatial patterns and temporal trends to inform large-scale flood risk management decisions and policies. In this paper, we present different flood occurrence and impact models based upon statistical and machine learning methods over 31,000 watersheds spread across Canada and the US. The models can be quickly calibrated and thereby easily run predictions over thousands of scenarios in a matter of minutes. As applications of the models, we present the geographical distribution of the modelled average annual number of people displaced due to flooding in Canada and the US, as well as various scenario analyses. We find for example that an increase of 10 % in average precipitation yields an increase of population displaced of 18 % in Canada and 14 % in the U.S. The model can therefore be used by a broad range of end-users ranging from climate scientists to economists who seek to translate climate and socioeconomic scenarios into flood probabilities and impacts measured in terms of population displaced.
- Open Access
- 26 February 2024
- Published by Copernicus GmbH
- Vol. 2024, 1
Comment on egusphere-2023-3039
Large-scale socioeconomic studies of the impacts of floods are difficult and costly for countries such as Canada and the United States due to the large number of rivers and size of watersheds. Such studies are however very important to analyze spatial patterns and temporal trends to inform large-scale flood risk management decisions and policies. In this paper, we present different flood occurrence and impact models based upon statistical and machine learning methods over 31,000 watersheds spread across Canada and the US. The models can be quickly calibrated and thereby easily run predictions over thousands of scenarios in a matter of minutes. As applications of the models, we present the geographical distribution of the modelled average annual number of people displaced due to flooding in Canada and the US, as well as various scenario analyses. We find for example that an increase of 10 % in average precipitation yields an increase of population displaced of 18 % in Canada and 14 % in the U.S. The model can therefore be used by a broad range of end-users ranging from climate scientists to economists who seek to translate climate and socioeconomic scenarios into flood probabilities and impacts measured in terms of population displaced.
- 26 February 2024
- Published by Copernicus GmbH
- Vol. 2024, 1
Open AccessComment on egusphere-2023-3039
Large-scale socioeconomic studies of the impacts of floods are difficult and costly for countries such as Canada and the United States due to the large number of rivers and size of watersheds. Such studies are however very important to analyze spatial patterns and temporal trends to inform large-scale flood risk management decisions and policies. In this paper, we present different flood occurrence and impact models based upon statistical and machine learning methods over 31,000 watersheds spread across Canada and the US. The models can be quickly calibrated and thereby easily run predictions over thousands of scenarios in a matter of minutes. As applications of the models, we present the geographical distribution of the modelled average annual number of people displaced due to flooding in Canada and the US, as well as various scenario analyses. We find for example that an increase of 10 % in average precipitation yields an increase of population displaced of 18 % in Canada and 14 % in the U.S. The model can therefore be used by a broad range of end-users ranging from climate scientists to economists who seek to translate climate and socioeconomic scenarios into flood probabilities and impacts measured in terms of population displaced.