Global projections of heat stress at high temporal resolution using machine learning

<p>Climate change poses a significant threat to agriculture, with potential impacts on food security, economic stability, and human livelihoods. Dairy cattle, a crucial component of the livestock sector, are particularly vulnerable to heat stress, which can adversely affect milk production, im...

Full description

Saved in:
Bibliographic Details
Main Authors: P. Georgiades, T. Economou, Y. Proestos, J. Araya, J. Lelieveld, M. Neira
Format: Article
Language:English
Published: Copernicus Publications 2025-03-01
Series:Earth System Science Data
Online Access:https://essd.copernicus.org/articles/17/1153/2025/essd-17-1153-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850218587050999808
author P. Georgiades
P. Georgiades
T. Economou
T. Economou
Y. Proestos
J. Araya
J. Lelieveld
J. Lelieveld
M. Neira
author_facet P. Georgiades
P. Georgiades
T. Economou
T. Economou
Y. Proestos
J. Araya
J. Lelieveld
J. Lelieveld
M. Neira
author_sort P. Georgiades
collection DOAJ
description <p>Climate change poses a significant threat to agriculture, with potential impacts on food security, economic stability, and human livelihoods. Dairy cattle, a crucial component of the livestock sector, are particularly vulnerable to heat stress, which can adversely affect milk production, immune function, and feed intake and, in extreme cases, lead to mortality. The Temperature Humidity Index (THI) is a widely used metric to quantify the combined effects of temperature and humidity on cattle. However, the THI was previously estimated using daily-level data, which do not capture the daily thermal load and cumulative heat stress, especially during nights when cooling is inadequate. To address this limitation, we developed a machine learning approach to temporally downscale daily climate data to hourly THI values. Utilizing historical ERA5 reanalysis data, we trained an XGBoost model and generated hourly THI datasets for 12 NEX-GDDP-CMIP6 climate models under two emission scenarios (SSP2-4.5 and SSP5-8.5) extending to the end of the century. These high-resolution THI data provide an accurate quantification of heat stress in dairy cattle, enabling improved predictions and management strategies to mitigate the impacts of climate change on this vital agricultural sector. The dataset created in this study is publicly available at <a href="https://doi.org/10.26050/WDCC/THI">https://doi.org/10.26050/WDCC/THI</a> <span class="cit" id="xref_paren.1">(<a href="#bib1.bibx17">Georgiades</a>, <a href="#bib1.bibx17">2024</a><a href="#bib1.bibx17">b</a>)</span>.</p>
format Article
id doaj-art-b7b992bdbe824a078c43e8d09bd37fbc
institution OA Journals
issn 1866-3508
1866-3516
language English
publishDate 2025-03-01
publisher Copernicus Publications
record_format Article
series Earth System Science Data
spelling doaj-art-b7b992bdbe824a078c43e8d09bd37fbc2025-08-20T02:07:40ZengCopernicus PublicationsEarth System Science Data1866-35081866-35162025-03-01171153117110.5194/essd-17-1153-2025Global projections of heat stress at high temporal resolution using machine learningP. Georgiades0P. Georgiades1T. Economou2T. Economou3Y. Proestos4J. Araya5J. Lelieveld6J. Lelieveld7M. Neira8Computation-based Science and Technology Research Center CaSToRC, The Cyprus Institute, Nicosia, CyprusClimate and Atmosphere Research Center (CARE-C), The Cyprus Institute, Nicosia, CyprusClimate and Atmosphere Research Center (CARE-C), The Cyprus Institute, Nicosia, CyprusDepartment of Mathematics and Statistics, University of Exeter, Exeter, UKClimate and Atmosphere Research Center (CARE-C), The Cyprus Institute, Nicosia, CyprusClimate and Atmosphere Research Center (CARE-C), The Cyprus Institute, Nicosia, CyprusClimate and Atmosphere Research Center (CARE-C), The Cyprus Institute, Nicosia, CyprusMax Planck Institute for Chemistry, Mainz, GermanyClimate and Atmosphere Research Center (CARE-C), The Cyprus Institute, Nicosia, Cyprus<p>Climate change poses a significant threat to agriculture, with potential impacts on food security, economic stability, and human livelihoods. Dairy cattle, a crucial component of the livestock sector, are particularly vulnerable to heat stress, which can adversely affect milk production, immune function, and feed intake and, in extreme cases, lead to mortality. The Temperature Humidity Index (THI) is a widely used metric to quantify the combined effects of temperature and humidity on cattle. However, the THI was previously estimated using daily-level data, which do not capture the daily thermal load and cumulative heat stress, especially during nights when cooling is inadequate. To address this limitation, we developed a machine learning approach to temporally downscale daily climate data to hourly THI values. Utilizing historical ERA5 reanalysis data, we trained an XGBoost model and generated hourly THI datasets for 12 NEX-GDDP-CMIP6 climate models under two emission scenarios (SSP2-4.5 and SSP5-8.5) extending to the end of the century. These high-resolution THI data provide an accurate quantification of heat stress in dairy cattle, enabling improved predictions and management strategies to mitigate the impacts of climate change on this vital agricultural sector. The dataset created in this study is publicly available at <a href="https://doi.org/10.26050/WDCC/THI">https://doi.org/10.26050/WDCC/THI</a> <span class="cit" id="xref_paren.1">(<a href="#bib1.bibx17">Georgiades</a>, <a href="#bib1.bibx17">2024</a><a href="#bib1.bibx17">b</a>)</span>.</p>https://essd.copernicus.org/articles/17/1153/2025/essd-17-1153-2025.pdf
spellingShingle P. Georgiades
P. Georgiades
T. Economou
T. Economou
Y. Proestos
J. Araya
J. Lelieveld
J. Lelieveld
M. Neira
Global projections of heat stress at high temporal resolution using machine learning
Earth System Science Data
title Global projections of heat stress at high temporal resolution using machine learning
title_full Global projections of heat stress at high temporal resolution using machine learning
title_fullStr Global projections of heat stress at high temporal resolution using machine learning
title_full_unstemmed Global projections of heat stress at high temporal resolution using machine learning
title_short Global projections of heat stress at high temporal resolution using machine learning
title_sort global projections of heat stress at high temporal resolution using machine learning
url https://essd.copernicus.org/articles/17/1153/2025/essd-17-1153-2025.pdf
work_keys_str_mv AT pgeorgiades globalprojectionsofheatstressathightemporalresolutionusingmachinelearning
AT pgeorgiades globalprojectionsofheatstressathightemporalresolutionusingmachinelearning
AT teconomou globalprojectionsofheatstressathightemporalresolutionusingmachinelearning
AT teconomou globalprojectionsofheatstressathightemporalresolutionusingmachinelearning
AT yproestos globalprojectionsofheatstressathightemporalresolutionusingmachinelearning
AT jaraya globalprojectionsofheatstressathightemporalresolutionusingmachinelearning
AT jlelieveld globalprojectionsofheatstressathightemporalresolutionusingmachinelearning
AT jlelieveld globalprojectionsofheatstressathightemporalresolutionusingmachinelearning
AT mneira globalprojectionsofheatstressathightemporalresolutionusingmachinelearning