Marie‐Jeanne Gnacoussa Sambou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Marie‐Jeanne Gnacoussa Sambou has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Abul Ehsan Bhuiyan
National Center for Environmental Prediction (NCEP), National Oceanic and Atmospheric Administration (NOAA), College Park, MD 20740, USA
2 shared publications - Adama Faye
Institut de Santé et Développement (ISED), Université Cheikh Anta Diop (UCAD), Dakar BP 5005, Senegal
2 shared publications - Aida Diongue Niang
Agence Nationale de l’Aviation Civile et de la Météorologie (ANACIM), Dakar BP 8184, Senegal
2 shared publications - Amadou Thierno Gaye
Laboratoire Physique de l’Atmosphère et de l’Océan-Siméon Fongang (LPAO-SF), Ecole Supérieure Polytechnique (ESP), Université Cheikh Anta Diop de Dakar, Dakar-Fann 5085, Dakar, Senegal
2 shared publications Daouda Badiane
LPAOSF, ESP Univ. Cheikh Anta Diop Dakar Dakar Senegal
2 shared publications- Daouda Badiane
Laboratoire de Physique de l’Atmosphère et de l’Ocean–Simeon Fongang (LPAO-SF), Ecole Superieure Polytechnique, Universite Cheikh Anta Diop (UCAD), Dakar BP 5085, Senegal
2 shared publications
Latest Publications
- Open Access
- 28 August 2025
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 22 (9) , 1349
Machine Learning-Based Prediction of Heatwave-Related Hospitalizations: A Case Study in Matam, Senegal
This study assesses the impact of heatwaves on hospital admissions in the Matam region of Senegal by combining climatic indices with machine learning methods. Using daily maximum temperature (TMAX) and heat index (HI), heatwave events were identified from 2017 to 2022. Hospital data from Ourossogui Regional Hospital were analyzed, and three predictive models, Random Forest (RF), Extreme Gradient Boosting (XGB), and Generalized Additive Models (GAMs), were compared. A bootstrapping approach with 1000 iterations was used to evaluate model robustness. The findings reveal a significant delayed effect of heatwaves, with increased hospitalizations occurring three to five days after the event. RF outperformed the other models with R2 values ranging from 0.51 to 0.72. These findings highlight the need to enhance heatwave monitoring and promote the integration of impact-based climate forecasting into health early warning systems, particularly to protect vulnerable groups such as the elderly, children, and outdoor workers.
- 28 August 2025
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 22 (9) , 1349
Open AccessMachine Learning-Based Prediction of Heatwave-Related Hospitalizations: A Case Study in Matam, Senegal
This study assesses the impact of heatwaves on hospital admissions in the Matam region of Senegal by combining climatic indices with machine learning methods. Using daily maximum temperature (TMAX) and heat index (HI), heatwave events were identified from 2017 to 2022. Hospital data from Ourossogui Regional Hospital were analyzed, and three predictive models, Random Forest (RF), Extreme Gradient Boosting (XGB), and Generalized Additive Models (GAMs), were compared. A bootstrapping approach with 1000 iterations was used to evaluate model robustness. The findings reveal a significant delayed effect of heatwaves, with increased hospitalizations occurring three to five days after the event. RF outperformed the other models with R2 values ranging from 0.51 to 0.72. These findings highlight the need to enhance heatwave monitoring and promote the integration of impact-based climate forecasting into health early warning systems, particularly to protect vulnerable groups such as the elderly, children, and outdoor workers.
- Open Access
- 25 March 2025
- Published by MDPI AG in Preprints.org
Machine Learning‐Based Prediction of Heatwave‐Related Hospitalizations: A Case Study in Matam, Senegal
This study analyzes the impact of heatwaves on hospital admissions in the Matam region, Senegal, by integrating climate modeling and advanced machine-learning techniques. Given the increasing frequency and severity of heatwaves, particularly in vulnerable regions such as the Sahel, it is critical to understand their health impacts to enhance public health responses. The primary objective of this research is to characterize the temporal dynamics of heatwave-induced hospitalizations and to identify key climatic and socio-demographic factors influencing these admissions. Our methodological approach involved detecting and characterizing heatwaves using climatic indices, such as daily maximum temperatures (TMAX) and maximum heat index (HI), and assessing their impacts on hospital admissions using Ourossogui Regional Hospital data from January 2017 to May 2022. Advanced predictive models, including Random Forest (RF), Extreme Gradient Boosting (XGB), and traditional Generalized Additive Models (GAM), were developed and compared to evaluate their effectiveness in capturing complex interactions between climatic and health variables. To ensure the robustness of our findings, a bootstrapping approach with 1000 iterations was applied, allowing for the estimation of confidence intervals and reducing dependence on a single training sample. The results revealed a significant delayed increase in hospitalizations occurring approximately three to five days after heatwave events, suggesting that physiological deterioration and behavioral factors, such as delayed health-seeking due to environmental constraints and social behaviors, contribute to this latency. Among the predictive models tested, RF achieved the best performance with an R² of [0.51; 0.72], clearly outperforming traditional statistical approaches. Bootstrapping further confirmed the stability of these predictions, reinforcing the reliability of machine learning models in climate-health studies. These findings highlight the critical need for enhancing heatwave monitoring and establishing robust early-warning systems. Integrating climate predictions into public health strategies could significantly improve preparedness and enable health systems to respond more effectively to extreme heat events. Targeted prevention measures, particularly focused on vulnerable groups such as the elderly, children, and outdoor workers, should be prioritized. In future research, incorporating additional environmental factors such as air pollution, wind, and others could further refine predictions. Moreover, expanding the study to include a greater number of healthcare facilities and integrating vulnerability factors such as the availability of healthcare structures, access to potable water, energy access, vegetation cover, hydrology, mobile network coverage, poverty dimension, and other socioeconomic indicators would enhance the analysis. The use of advanced Deep Learning techniques could also improve prediction accuracy by effectively modeling complex and nonlinear interactions. Additionally, it would be relevant to extend the study to other regions particularly vulnerable to extreme heat, to gain a more comprehensive understanding of its health and climatic impacts.
- 25 March 2025
- Published by MDPI AG in Preprints.org
Open AccessMachine Learning‐Based Prediction of Heatwave‐Related Hospitalizations: A Case Study in Matam, Senegal
This study analyzes the impact of heatwaves on hospital admissions in the Matam region, Senegal, by integrating climate modeling and advanced machine-learning techniques. Given the increasing frequency and severity of heatwaves, particularly in vulnerable regions such as the Sahel, it is critical to understand their health impacts to enhance public health responses. The primary objective of this research is to characterize the temporal dynamics of heatwave-induced hospitalizations and to identify key climatic and socio-demographic factors influencing these admissions. Our methodological approach involved detecting and characterizing heatwaves using climatic indices, such as daily maximum temperatures (TMAX) and maximum heat index (HI), and assessing their impacts on hospital admissions using Ourossogui Regional Hospital data from January 2017 to May 2022. Advanced predictive models, including Random Forest (RF), Extreme Gradient Boosting (XGB), and traditional Generalized Additive Models (GAM), were developed and compared to evaluate their effectiveness in capturing complex interactions between climatic and health variables. To ensure the robustness of our findings, a bootstrapping approach with 1000 iterations was applied, allowing for the estimation of confidence intervals and reducing dependence on a single training sample. The results revealed a significant delayed increase in hospitalizations occurring approximately three to five days after heatwave events, suggesting that physiological deterioration and behavioral factors, such as delayed health-seeking due to environmental constraints and social behaviors, contribute to this latency. Among the predictive models tested, RF achieved the best performance with an R² of [0.51; 0.72], clearly outperforming traditional statistical approaches. Bootstrapping further confirmed the stability of these predictions, reinforcing the reliability of machine learning models in climate-health studies. These findings highlight the critical need for enhancing heatwave monitoring and establishing robust early-warning systems. Integrating climate predictions into public health strategies could significantly improve preparedness and enable health systems to respond more effectively to extreme heat events. Targeted prevention measures, particularly focused on vulnerable groups such as the elderly, children, and outdoor workers, should be prioritized. In future research, incorporating additional environmental factors such as air pollution, wind, and others could further refine predictions. Moreover, expanding the study to include a greater number of healthcare facilities and integrating vulnerability factors such as the availability of healthcare structures, access to potable water, energy access, vegetation cover, hydrology, mobile network coverage, poverty dimension, and other socioeconomic indicators would enhance the analysis. The use of advanced Deep Learning techniques could also improve prediction accuracy by effectively modeling complex and nonlinear interactions. Additionally, it would be relevant to extend the study to other regions particularly vulnerable to extreme heat, to gain a more comprehensive understanding of its health and climatic impacts.
- Open Access
- 25 November 2024
- Published by MDPI AG in Atmosphere
- Vol. 15 (12) , 1413
Dust Content Modulation and Spring Heat Waves in Senegal (2003–2022)
The population of Senegal faces health challenges related to desert dust and heat waves (HWs). This study aims to (a) update the documentation of HWs in Senegal, expanding on the work of Sambou et al. (2019); (b) investigate the modulation of dust indicators during HWs; and (c) assess the distinct impacts of dust content on night-time and daytime HWs. We use [i] the daily maximum air temperature (Tx), minimum air temperature (Tn), and apparent temperature (Ta) from 12 stations in the Global Surface Summary of the Day (GSOD) database and [ii] the Dust Aerosol Optical Depth (Dust AOD), particulate matter (PM) concentrations, 925 hPa wind, and Mean Sea Level Pressure (MSLP) from the Copernicus Atmosphere Monitoring Service (CAMS) reanalysis. HWs are defined for each station in spring as periods when Tx, Tn, or Ta exceeds the 95th percentile for at least three consecutive days. Three homogeneous zones from the Atlantic coast to inland Senegal are identified using hierarchical cluster analysis: Zone 1 (Saint-Louis, Dakar-Yoff, Ziguinchor, and Cap Skirring), Zone 2 (Podor, Linguère, Diourbel, and Kaolack), and Zone 3 (Matam, Tambacounda, Kédougou, and Kolda). Our results show that Zone 1 records the highest number of HWs for Tx, Tn, and Ta, while Zone 3 experiences more HWs in terms of Tn and Ta than Zone 2. The influence of dust is notably stronger for HWs linked to Tn and Ta than for those related to Tx. Analysis of the mechanisms shows that the presence of dust in Senegal and its surrounding regions is detected up to four days before the onset of HWs. These findings suggest that dust conditions associated with spring HWs in Senegal may be better distinguished and predicted.
- 25 November 2024
- Published by MDPI AG in Atmosphere
- Vol. 15 (12) , 1413
Open AccessDust Content Modulation and Spring Heat Waves in Senegal (2003–2022)
The population of Senegal faces health challenges related to desert dust and heat waves (HWs). This study aims to (a) update the documentation of HWs in Senegal, expanding on the work of Sambou et al. (2019); (b) investigate the modulation of dust indicators during HWs; and (c) assess the distinct impacts of dust content on night-time and daytime HWs. We use [i] the daily maximum air temperature (Tx), minimum air temperature (Tn), and apparent temperature (Ta) from 12 stations in the Global Surface Summary of the Day (GSOD) database and [ii] the Dust Aerosol Optical Depth (Dust AOD), particulate matter (PM) concentrations, 925 hPa wind, and Mean Sea Level Pressure (MSLP) from the Copernicus Atmosphere Monitoring Service (CAMS) reanalysis. HWs are defined for each station in spring as periods when Tx, Tn, or Ta exceeds the 95th percentile for at least three consecutive days. Three homogeneous zones from the Atlantic coast to inland Senegal are identified using hierarchical cluster analysis: Zone 1 (Saint-Louis, Dakar-Yoff, Ziguinchor, and Cap Skirring), Zone 2 (Podor, Linguère, Diourbel, and Kaolack), and Zone 3 (Matam, Tambacounda, Kédougou, and Kolda). Our results show that Zone 1 records the highest number of HWs for Tx, Tn, and Ta, while Zone 3 experiences more HWs in terms of Tn and Ta than Zone 2. The influence of dust is notably stronger for HWs linked to Tn and Ta than for those related to Tx. Analysis of the mechanisms shows that the presence of dust in Senegal and its surrounding regions is detected up to four days before the onset of HWs. These findings suggest that dust conditions associated with spring HWs in Senegal may be better distinguished and predicted.
- Open Access
- 6 May 2021
- Published by Wiley in International Journal of Climatology
- Vol. 41 (14) , 6238-6253
Heat waves in spring from Senegal to Sahel: Evolution under climate change
- 6 May 2021
- Published by Wiley in International Journal of Climatology
- Vol. 41 (14) , 6238-6253
Open AccessHeat waves in spring from Senegal to Sahel: Evolution under climate change
- Open Access
- 4 July 2019
- Published by Wiley in International Journal of Climatology
- Vol. 40 (1) , 440-457
Heat wave occurrences over Senegal during spring: Regionalization and synoptic patterns
Based on 12 Senegalese stations of the Global Summary of the Day (GSOD) database (1979–2014), heat waves (HW) are defined for each station in spring (March–April–May, the hottest season in Senegal) as the daily maximum temperature (Tx), minimum temperature (Tn), or average apparent temperature of the day (AT), exceeding the corresponding 95% mobile percentile for at least three consecutive days. A hierarchical cluster analysis used to regionalize HW in these 12 stations is applied to simultaneous occurrences of daily temperature peaks over their 95% mobile percentiles. Three homogeneous zones of four stations each are identified (Zone 1, Zone 2 and Zone 3), from west (Atlantic coastline) to east (inland Senegal). Atmospheric circulation associated with HW is assessed through composites of ERA‐Interim deseasonalized anomalies, with the start date of each HW in each zone used as a reference. The main pattern controlling the presence of HW in Senegal consists in positive pressure anomalies centred around the strait of Gibraltar, promoting easterly to northeasterly wind anomalies. This causes higher temperatures in the three zones of Senegal, and lower temperatures and drier air over the central Sahel. This pattern is opposite to that characteristic of HW in the central Sahel shown in previous studies. From Zone 1 to Zone 3, the temperature and moisture patterns are shifted to the east while pressure anomalies weaken drastically. Night‐time Tn‐HW are characterized by higher water vapour contents than daytime Tx‐HW, corroborating and complementing previous studies over the Sahel. These HW patterns are close to the canonical mode of intra‐seasonal atmospheric variability over Senegal.
- 4 July 2019
- Published by Wiley in International Journal of Climatology
- Vol. 40 (1) , 440-457
Open AccessHeat wave occurrences over Senegal during spring: Regionalization and synoptic patterns
Based on 12 Senegalese stations of the Global Summary of the Day (GSOD) database (1979–2014), heat waves (HW) are defined for each station in spring (March–April–May, the hottest season in Senegal) as the daily maximum temperature (Tx), minimum temperature (Tn), or average apparent temperature of the day (AT), exceeding the corresponding 95% mobile percentile for at least three consecutive days. A hierarchical cluster analysis used to regionalize HW in these 12 stations is applied to simultaneous occurrences of daily temperature peaks over their 95% mobile percentiles. Three homogeneous zones of four stations each are identified (Zone 1, Zone 2 and Zone 3), from west (Atlantic coastline) to east (inland Senegal). Atmospheric circulation associated with HW is assessed through composites of ERA‐Interim deseasonalized anomalies, with the start date of each HW in each zone used as a reference. The main pattern controlling the presence of HW in Senegal consists in positive pressure anomalies centred around the strait of Gibraltar, promoting easterly to northeasterly wind anomalies. This causes higher temperatures in the three zones of Senegal, and lower temperatures and drier air over the central Sahel. This pattern is opposite to that characteristic of HW in the central Sahel shown in previous studies. From Zone 1 to Zone 3, the temperature and moisture patterns are shifted to the east while pressure anomalies weaken drastically. Night‐time Tn‐HW are characterized by higher water vapour contents than daytime Tx‐HW, corroborating and complementing previous studies over the Sahel. These HW patterns are close to the canonical mode of intra‐seasonal atmospheric variability over Senegal.