Abstract
As heatwaves increase in both frequency and intensity globally, the need to develop tools to predict the human impact and develop a more comprehensive understanding of the impact mechanism at a population level is becoming more urgent. Our study provides a taxonomy of heatwaves based on identifying sub-threshold lethal heatwaves through physiological adaptation and vulnerability. We use a classification algorithm applied to a lethal heatwave dataset, comprising 125,411 events where the temperature exceeded the 90th percentile across 140 cities, with combined meteorology and sociodemographic inputs to label these events. The accuracy of our model outperforms classification that relies on wet bulb temperature thresholds with a factor of 11 improvement in imbalanced classification performance. Furthermore, we find that the majority of lethal heatwaves within our dataset occur below high wet bulb temperature thresholds and that accurate predictions for heatwave mortality can be obtained by combining thermo-temporal differentials and population health metrics instead of absolute climatic conditions. We thus propose classifying heatwaves as either: Shock Heatwaves, where aggressive thermo-temporal differentials from a local acclimation point trigger adverse stress effects, particularly among the vulnerable; or Threshold Heatwaves, where high temperature and humidity conditions do exceed the ability to dissipate heat effectively.
Similar content being viewed by others
Data availability
The lethal/non-lethal heatwave labels have been made available by Dousset and contributors71 through the following repository https://doi.org/10.5281/zenodo.18528487. ERA5 reanalysis variables can be obtained from https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-pressure-levels. Population data is available from https://population.un.org/wpp/. BMI data is available from 10.5281/zenodo.10534960. SDI data is available from 10.6069/dwqg-3z75.
Code availability
The code for this paper is available at https://doi.org/10.5281/zenodo.18430720. This codebase provides a blueprint to download the requisite data through querying their respective APIs, compile the database, train and test the model, and generate key figures. The random forests were implemented using Scikit-learn72 and SMOTE using imbalanced-learn73.
References
Vicedo-Cabrera, A. M. et al. The burden of heat-related mortality attributable to recent human-induced climate change. Nat. Clim. Chang. 11, 492–500 (2021).
Gasparrini, A. et al. Projections of temperature-related excess mortality under climate change scenarios. Lancet Planet. Health 1, e360–e367 (2017).
Boni, Z. et al. What is a heat(wave)? an interdisciplinary perspective. Clim. Chang. 176, 129 (2023).
Schwingshackl, C., Sillmann, J., Vicedo-Cabrera, A. M., Sandstad, M. & Aunan, K. Heat stress indicators in cmip6: estimating future trends and exceedances of impact-relevant thresholds. Earth’s Future 9, e2020EF001885 (2021).
Conlon, K. C. et al. Mapping human vulnerability to extreme heat: a critical assessment of heat vulnerability indices created using principal components analysis. Environ. Health Perspect. 128, 97001 (2020).
Son, J.-Y., Liu, J. C. & Bell, M. L. Temperature-related mortality: a systematic review and investigation of effect modifiers. Environ. Res. Lett. 14, 073004 (2019).
Benmarhnia, T., Deguen, S., Kaufman, J. S. & Smargiassi, A. Vulnerability to heat-related mortality: A systematic review, meta-analysis, and meta-regression analysis. Epidemiology 26, 781–793 (2015).
Arsad, F. S. et al. The impact of heatwaves on mortality and morbidity and the associated vulnerability factors: a systematic review. Int. J. Environ. Res. Public Health 19, 16356 (2022).
Bakhtsiyarava, M. et al. Modification of temperature-related human mortality by area-level socioeconomic and demographic characteristics in Latin American cities. Soc. Sci. Med. 317, 115526 (2023).
Mora, C. et al. Global risk of deadly heat. Nat. Clim. Chang. 7, 501–506 (2017).
Ebi, K. L. et al. Hot weather and heat extremes: health risks. Lancet 398, 698–708 (2021).
Rocklöv, J., Ebi, K. & Forsberg, B. Mortality related to temperature and persistent extreme temperatures—a study of cause-specific and age stratified mortality. Epidemiology 22, S13 (2011).
Khatana, S. A. M., Werner, R. M. & Groeneveld, P. W. Association of extreme heat with all-cause mortality in the contiguous us, 2008-2017. JAMA Netw. Open 5, e2212957–e2212957 (2022).
Kephart, J. L. et al. City-level impact of extreme temperatures and mortality in Latin America. Nat. Med. 28, 1700–1705 (2022).
Ballester, J. et al. Heat-related mortality in Europe during the summer of 2022. Nat. Med. 29, 1857–1866 (2023).
Kovats, R. S. & Hajat, S. Heat stress and public health: a critical review. Annu. Rev. Public Health 29, 41–55 (2008).
Bouchama, A. & Knochel, J. P. Heat stroke. N. Engl. J. Med. 346, 1978–1988 (2002).
Keatinge, W. R. et al. Increased platelet and red cell counts, blood viscosity, and plasma cholesterol levels during heat stress, and mortality from coronary and cerebral thrombosis. Am. J. Med. 81, 795–800 (1986).
Sherwood, S. C. & Huber, M. An adaptability limit to climate change due to heat stress. Proc. Natl. Acad. Sci. 107, 9552–9555 (2010).
Pal, J. S. & Eltahir, E. A. B. Future temperature in southwest Asia projected to exceed a threshold for human adaptability. Nat. Clim. Change 6, 197–200 (2016).
Vecellio, D. J., Wolf, S. T., Cottle, R. M. & Kenney, W. L. Evaluating the 35°C wet-bulb temperature adaptability threshold for young, healthy subjects (PSU HEAT Project). J. Appl. Physiol. 132, 340–345 (2022).
Donaldson, G. & Keatinge, W. Direct effects of rising temperatures on mortality in the UK. In Health Effects of Climate Change in the UK 2008 http://data.parliament.uk/DepositedPapers/Files/DEP2008-0556/DEP2008-0556.pdf (Health Protection Agency, Didcot, Oxfordshire, 2008).
Armstrong, B. G. et al. Association of mortality with high temperatures in a temperate climate: England and Wales. J. Epidemiol. Community Health 65, 340–345 (2011).
Simpson, C. H., Brousse, O., Ebi, K. L. & Heaviside, C. Commonly used indices disagree about the effect of moisture on heat stress. npj Clim. Atmos. Sci. 6, 78 (2023).
Lo, Y. T. E. et al. Optimal heat stress metric for modelling heat-related mortality varies from country to country. Int. J. Climatol. 43, 5553–5568 (2023).
Mohammad, P. & Weng, Q. Comparing existing heat wave indices in identifying dangerous heat wave outdoor conditions. Nexus 1, 100027 (2024).
UK Health Security Agency. User guide: weather-health alerting system https://assets.publishing.service.gov.uk/media/67f3aeaed3f1efd2ce2ab897/WHA_User_Guide.pdf (2025).
Debnath, R., Bardhan, R. & Bell, M. L. Lethal heatwaves are challenging India’s sustainable development. PLOS Clim. 2, e0000156 (2023).
Canouï-Poitrine, F., Cadot, E., Spira, A. & Spira, A. Excess deaths during the August 2003 heat wave in Paris, France. Rev.’Épidémiol. Santé Publique 54, 127–135 (2006).
Weisskopf, M. G. et al. Heat wave morbidity and mortality, Milwaukee, Wis, 1999 vs 1995: an improved response? Am. J. Public Health 92, 830–833 (2002).
Stull, R. Wet-bulb temperature from relative humidity and air temperature. J. Appl. Meteorol. Climatol. 50, 2267–2269 (2011).
Abarca-Gómez, L. & NCD Risk Factor Collaboration (NCD-RisC) Worldwide trends in body-mass index, underweight, overweight, and obesity from 1975 to 2016: a pooled analysis of 2416 population-based measurement studies in 128.9 million children, adolescents, and adults. Lancet 390, 2627–2642 (2017).
United Nations, Department of Economic and Social Affairs, Population Division. World Population Prospects: The 2022 Revision. https://population.un.org/dataportal/ (2022).
Kivimäki, M. et al. Body-mass index and risk of obesity-related complex multimorbidity: an observational multicohort study. Lancet Diab. Endocrinol. 10, 253–263 (2022).
Guh, D. P. et al. The incidence of co-morbidities related to obesity and overweight: a systematic review and meta-analysis. BMC Public Health 9, 88 (2009).
The GBD 2015 Obesity Collaborators Health effects of overweight and obesity in 195 countries over 25 years. N. Engl. J. Med. 377, 13–27 (2017).
Institute For Health Metrics And Evaluation. Global Burden of Disease Study 2021 (GBD 2021) Socio-Demographic Index (SDI) 1950–2021 https://ghdx.healthdata.org/node/548352 (2024).
Ton, M. J. et al. A global dataset of 7 billion individuals with socio-economic characteristics. Sci. Data 11, 1096 (2024).
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).
Hastie, T., Tibshirani, R. & Friedman, J. The Elements of Statistical Learning. Springer Series in Statistics. https://doi.org/10.1007/978-0-387-84858-7 (Springer New York, 2009).
Bechtel, B. & Daneke, C. Classification of local climate zones based on multiple earth observation data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 5, 1191–1202 (2012).
Cutler, D. R. et al. RANDOM FORESTS FOR CLASSIFICATION IN ECOLOGY. Ecology 88, 2783–2792 (2007).
Gislason, P., Benediktsson, J. & Sveinsson, J. Random forest classification of multisource remote sensing and geographic data. In IEEE International IEEE International IEEE International Geoscience and Remote Sensing Symposium, 2004. IGARSS ’04. Proceedings. 2004 Vol. 2, 1049–1052. http://ieeexplore.ieee.org/document/1368591/ (IEEE, Anchorage, AK, USA, 2004).
Gislason, P. O., Benediktsson, J. A. & Sveinsson, J. R. Random forests for land cover classification. Pattern Recognit. Lett. 27, 294–300 (2006).
Prasad, A. M., Iverson, L. R. & Liaw, A. Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9, 181–199 (2006).
Cafri, G., Li, L., Paxton, E. W. & Fan, J. Predicting risk for adverse health events using random forest. J. Appl. Stat. 45, 2279–2294 (2018).
Iwendi, C. et al. COVID-19 patient health prediction using boosted random forest algorithm. Front. Public Health 8, 357 (2020).
Khalilia, M., Chakraborty, S. & Popescu, M. Predicting disease risks from highly imbalanced data using random forest. BMC Med. Inform. Decis. Mak. 11, 51 (2011).
Khoshgoftaar, T. M., Golawala, M. & Hulse, J. V. An Empirical Study of Learning from Imbalanced Data Using Random Forest. In 19th IEEE International Conference on Tools with Artificial Intelligence(ICTAI 2007) Vol. 2, 310–317 (IEEE, 2007).
Platt, J. et al. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classif. 10, 61–74 (1999).
Fisher, A., Rudin, C. & Dominici, F. All models are wrong, but many are useful: learning a variable’s importance by studying an entire class of prediction models simultaneously. J. Mach. Learn. Res. 20, 1–81 (2019).
Kent, J. T. Information gain and a general measure of correlation. Biometrika 70, 163–173 (1983).
Chen, J. & Dai, A. The Atmosphere Has Become Increasingly Unstable During 1979–2020 Over the Northern Hemisphere. Geophys. Res. Lett. 50, e2023GL106125 (2023).
Curriero, F. C. Temperature and mortality in 11 cities of the eastern United States. Am. J. Epidemiol. 155, 80–87 (2002).
Donaldson, G., Kovats, S., Keatinge, W. & McMichael, A. Heat- and cold-related mortality and morbidity and climate change. Health Effects of Climate Change in the UK 70–80 (2001).
Cheng, J. et al. Cardiorespiratory effects of heatwaves: a systematic review and meta-analysis of global epidemiological evidence. Environ. Res. 177, 108610 (2019).
Burton, J. L. & Underwood, J. Clinical, educational, and epidemiological value of autopsy. Lancet 369, 1471–1480 (2007).
Shojania, K. G., Burton, E. C., McDonald, K. M. & Goldman, L. Changes in rates of autopsy-detected diagnostic errors over time: a systematic review. JAMA 289, 2849 (2003).
Davis, L., Gertler, P., Jarvis, S. & Wolfram, C. Air conditioning and global inequality. Glob. Environ. Change 69, 102299 (2021).
Rowe, A. K. et al. Effectiveness of strategies to improve health-care provider practices in low-income and middle-income countries: a systematic review. Lancet Glob. Health 6, e1163–e1175 (2018).
Rizwan, A. M., Dennis, L. Y. & Liu, C. A review on the generation, determination and mitigation of Urban Heat Island. J. Environ. Sci. 20, 120–128 (2008).
Turnbull, A., Osborn, M. & Nicholas, N. Hospital autopsy: endangered or extinct? J. Clin. Pathol. 68, 601 (2015).
Friedman, J. H. Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, https://doi.org/10.1214/aos/1013203451.full (2001).
Hersbach, H. et al. ERA5 hourly data on single levels from 1979 to present https://doi.org/10.24381/cds.adbb2d47 (2018).
Hersbach, H. et al. The ERA5 global reanalysis. Q. J. R. Meteorol. Soc. 146, 1999–2049 (2020).
Sun, Y. Q. et al. Can AI weather models predict out-of-distribution gray swan tropical cyclones? Proc. Natl. Acad. Sci. 122, e2420914122 (2025).
Japkowicz, N. & Stephen, S. The class imbalance problem: A systematic study. Intell. Data Anal. 6, 429–449 (2002).
More, A. S. & Rana, D. P. Review of random forest classification techniques to resolve data imbalance. In 2017 1st International Conference on Intelligent Systems and Information Management (ICISIM) 72–78 (IEEE, 2017).
Fernando, K. R. M. & Tsokos, C. P. Dynamically weighted balanced loss: class imbalanced learning and confidence calibration of deep neural networks. IEEE Trans. Neural Netw. Learn. Syst. 33, 2940–2951 (2022).
Chawla, N. V., Bowyer, K. W., Hall, L. O. & Kegelmeyer, W. P. SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002).
Dousset, B. Global risk of deadly heat data subset [90th percentile] https://doi.org/10.5281/zenodo.18528488 (2026).
Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Lemai^tre, G., Nogueira, F. & Aridas, C. K. Imbalanced-learn: a Python toolbox to tackle the curse of imbalanced datasets in machine learning. J. Mach. Learn. Res. 18, 1–5 (2017).
Met Office. Cartopy: a cartographic Python library with a matplotlib interface http://scitools.org.uk/cartopy (2010).
Acknowledgements
The authors would like to thank Rick Lewis, of the Centre for Landscape Regeneration at Cambridge University, for reviewing this work. RER’s acknowledges funding from The Royal Commission for the Exhibition of 1851 and EPSRC grant EP/R512461/1. RD acknowledges support from the Bill & Melinda Gates Foundation [OPP1144] and the Cambridge Humanities Research Grant. W.T. acknowledges funding from Deepmind, Huawei, and EPSRC grant EP/W002965/1.
Author information
Authors and Affiliations
Contributions
C.M. and B.D. compiled the initial lethal heatwave dataset. R.E.R., D.A.R., J.S.H., A.M. and E.S. conceived the work. R.E.R. and D.A.R. developed the approach. R.E.R. implemented and trained the model with guidance from W.T. and A.M. and R.E.R. wrote the code. R.E.R. and W.T. conducted the analysis with input and feedback from all authors. R.E.R. with input from E.S. completed the visualisation. R.E.R., D.A.R., R.D. and W.T. wrote the draft manuscript contributions and feedback from all authors. J.S.H., A.M. and E.S. provided supervision and funding acquisition.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Peer review
Peer review information
Nature Communications thanks Zhiwei Xu and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. A peer review file is available.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Rouse, R.E., Debnath, R., Rouse, D.A. et al. Reclassifying lethal heat. Nat Commun (2026). https://doi.org/10.1038/s41467-026-71396-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41467-026-71396-x
