Forecasting European temperature-related mortality in Summer 2024: data-driven vs. physics-based forecast approaches
- 1Uppsala University (Uppsala, Sweden)
- 2University of Bern (Bern, Switzerland)
Abstract
Heat has emerged as a major public health concern. Over 62 000 heat-related deaths were estimated to have occurred during the European summer of 2024, exemplifying the pressing need to develop effective early warning systems. Such systems depend critically on the quality of the underlying forecasts, and recent work has focused on developing impact-based forecasts for heat-related mortality, which provide impact-oriented information. To date, heat-related mortality forecasts have been based on the output of numerical weather prediction models, or physics-based forecasts. The field of weather forecasting is undergoing a rapid transformation with the advent of skillful data-driven forecasts. This case study compares European temperature-related mortality forecasts for summer 2024 based on physics-based weather forecasts with those based on data-driven weather forecasts. Our results highlight that both the physics-based and data-driven forecasts systematically underestimate temperature-related mortality, more pronouncedly so in the latter. Both types of forecasts appear sensitive to forecast errors at hot temperatures, due to the non-linear relationship between temperature and mortality. Nevertheless, temperature-related mortality forecasts based on data-driven weather forecasts appear to be a promising alternative to traditional physics-based weather forecasts, and targeted improvement of the representation of hot temperatures through bias correction or adjustment of the loss function to give greater weighting to hot temperatures could be beneficial for temperature-related mortality forecasting. We suggest the application of this approach to both data-driven and physics-based forecast ensembles as an important next step in the continued development of informative, impact-oriented forecasts.
Versions
Related
- GLoR-forecast: state-contingent global-local text routing for financial and socio-economic time-series forecasting
- Progress but not on track: forecasting under-five mortality and the likelihood of achieving SDG target 3.2 in Southern Africa
- Effects of European Bilberry Extract on Skin Aging Associated with Consumption of a High Temperature Roasted Diet in Rats
- Next-Generation Sequencing in Practical Wildlife Disease Investigation: Metagenomic Insights into European Bison and Gazelle Mortality and Morbidity Events.
- Mortality forecasting under climate risk: a stochastic approach with distributed lag nonlinear models
BibTeX
@article{holmberg2026forecasting,
title = {{Forecasting European temperature-related mortality in Summer 2024: data-driven vs. physics-based forecast approaches}},
author = {Emma Holmberg and Leonardo Olivetti},
journal = {Natural Hazards and Earth System Sciences},
year = {2026},
month = oct,
doi = {10.5194/nhess-26-4825-2026},
url = {https://nhess.copernicus.org/articles/26/4825/2026/},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Forecasting European temperature-related mortality in Summer 2024: data-driven vs. physics-based forecast approaches
AU - Emma Holmberg
AU - Leonardo Olivetti
PY - 2026
DA - 2026/10/06
JO - Natural Hazards and Earth System Sciences
DO - 10.5194/nhess-26-4825-2026
UR - https://nhess.copernicus.org/articles/26/4825/2026/
AB - Heat has emerged as a major public health concern. Over 62 000 heat-related deaths were estimated to have occurred during the European summer of 2024, exemplifying the pressing need to develop effective early warning systems. Such systems depend critically on the quality of the underlying forecasts, and recent work has focused on developing impact-based forecasts for heat-related mortality, which provide impact-oriented information. To date, heat-related mortality forecasts have been based on the output of numerical weather prediction models, or physics-based forecasts. The field of weather forecasting is undergoing a rapid transformation with the advent of skillful data-driven forecasts. This case study compares European temperature-related mortality forecasts for summer 2024 based on physics-based weather forecasts with those based on data-driven weather forecasts. Our results highlight that both the physics-based and data-driven forecasts systematically underestimate temperature-related mortality, more pronouncedly so in the latter. Both types of forecasts appear sensitive to forecast errors at hot temperatures, due to the non-linear relationship between temperature and mortality. Nevertheless, temperature-related mortality forecasts based on data-driven weather forecasts appear to be a promising alternative to traditional physics-based weather forecasts, and targeted improvement of the representation of hot temperatures through bias correction or adjustment of the loss function to give greater weighting to hot temperatures could be beneficial for temperature-related mortality forecasting. We suggest the application of this approach to both data-driven and physics-based forecast ensembles as an important next step in the continued development of informative, impact-oriented forecasts.
SN - 1684-9981
ER -