Original Articles Open access

Estimating indoor heat stress in broiler and swine facilities using high-resolution Geo-KOMPSAT-2A satellite data

Authors

Published
7 July 2026
Section
Original Articles
DOI
10.4081/jae.2026.2096

Abstract

Heat stress poses a critical challenge to animal welfare and productivity in intensive livestock production systems, particularly for broilers and swine with limited thermoregulatory capacity. The temperature-humidity index (THI) is widely applied to assess thermal stress, yet conventional monitoring methods remain constrained by limited spatial coverage and scalability. This study introduces a novel satellite-based framework for estimating indoor heat stress in livestock facilities using machine learning and GEO-KOMPSAT-2A (GK2A) satellite data. The proposed outside-in approach integrates satellite-derived temperature, humidity, and solar irradiance to infer indoor environmental conditions without reliance on on-site sensors or detailed building specifications. Unlike computational fluid dynamics models, which are resource-intensive and difficult to scale, this data-driven method captures nonlinear relationships between outdoor meteorological variables and indoor microclimates. The XGBoost model demonstrated superior accuracy in estimating indoor temperature and humidity across multiple farms. When converted to THI, relative root mean square errors (rRMSE) ranged from 0.623% to 0.693% in swine farms and 0.827% to 1.332% in broiler farms, demonstrating robust performance in heat stress assessment. By leveraging geostationary satellite observations with high temporal and spatial resolution, this framework enables continuous, large-scale monitoring of thermal conditions in livestock facilities. The approach provides a practical and scalable tool to support ventilation management, cooling strategies, and animal welfare decisions under dynamic weather conditions.

Keywords

Supporting Agencies

National Institute of Agricultural Sciences, Rural Development Administration, South Korea

Data Availability Statement

The datasets generated and/or analyzed during the current study are not publicly available due to confidentiality agreements with the collaborating farms, but are available upon reasonable request from the corresponding author.

References

  1. Al-Hadhrami LM, 2013. Comprehensive review of cooling and heating degree days characteristics over Kingdom of Saudi Arabia. Renew Sustain Energy Rev 27:305-314. DOI: https://doi.org/10.1016/j.rser.2013.04.034
  2. Blanes-Vidal V, Guijarro E, Balasch S, Torres AG, 2008. Application of computational fluid dynamics to the prediction of airflow in a mechanically ventilated commercial poultry building. Biosyst Eng 100:105-116. DOI: https://doi.org/10.1016/j.biosystemseng.2008.02.004
  3. Chapman NH, Chlingaryan A, Thomson PC, Lomax S, Islam MA, Doughty AK, Clark CEF, 2023. A deep learning model to forecast cattle heat stress. Comput Electron Agric 211:107932. DOI: https://doi.org/10.1016/j.compag.2023.107932
  4. Chen T, Guestrin C, 2016. XGBoost: A scalable tree boosting system. Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., San Francisco. Available from: https://www.kdd.org/kdd2016/papers/files/rfp0697-chenAemb.pdf DOI: https://doi.org/10.1145/2939672.2939785
  5. Deng S, Li Z, Wei Y, Wang Y, Li B, Zheng W, 2024. Assessing temperature distribution inside commercial stacked cage broiler houses in winter. Animals (Basel) 14:2638. DOI: https://doi.org/10.3390/ani14182638
  6. do Amaral Vercellino R, Nääs, I. de A., Moura, D.J. de, 2025. Tracking heat stress in broilers: a thermographic analysis of anatomical sensitivity across growth stages. Animals (Basel) 15:2233. DOI: https://doi.org/10.3390/ani15152233
  7. Georgiades P, Economou T, Proestos Y, Araya J, Lelieveld J, Neira M, 2025. Global projections of heat stress at high temporal resolution using machine learning. Earth Syst Sci Data 17:1153-1171. DOI: https://doi.org/10.5194/essd-17-1153-2025
  8. Hammer A, Heinemann D, Hoyer C, Kuhlemann R, Lorenz E, Müller R, Beyer HG, 2003. Solar energy assessment using remote sensing technologies. Remote Sens Environ 86:423-432. DOI: https://doi.org/10.1016/S0034-4257(03)00083-X
  9. Herbut P, Angrecka S, Walczak J, 2018. Environmental parameters to assessing of heat stress in dairy cattle—a review. Int J Biometeorol 62:2089-2097. DOI: https://doi.org/10.1007/s00484-018-1629-9
  10. Jang JC, Sohn EH, Park KH, 2022. Estimating hourly surface solar irradiance from GK2A/AMI Data using machine learning approach around Korea. Remote Sens 14:1840. DOI: https://doi.org/10.3390/rs14081840
  11. Kim HR, Seong P, Seol KH, Park JE, Kim H, Park W, et al., 2025. Effects of heat stress on growth performance, physiological responses, and carcass traits in broilers. J Therm Biol 127:103994. DOI: https://doi.org/10.1016/j.jtherbio.2024.103994
  12. Lee IB, Bitog JPP, Hong SW, Seo IH, Kwon KS, Bartzanas T, Kacira M, 2013. The past, present and future of CFD for agro-environmental applications. Comput Electron Agric 93:168-183. DOI: https://doi.org/10.1016/j.compag.2012.09.006
  13. Lin S, Gao W, Chen Y, Yao W, Fang Z, Guo C, Lu Z, 2026. Advancing thermal and humidity comfort assessment in hot-humid climates in summer through machine learning. Build Environ 288:113947. DOI: https://doi.org/10.1016/j.buildenv.2025.113947
  14. Liu C, Cao Y, Luo Z, Liu Y, Reynolds CK, Humphries D, et al., 2025. Heat stress monitoring, modelling, and mitigation in a dairy cattle building in reading, UK: Impacts of current and projected heatwaves. Build Environ 279:113046. DOI: https://doi.org/10.1016/j.buildenv.2025.113046
  15. Liu F, Zhao W, Le HH, Cottrell JJ, Green MP, Leury BJ, et al., 2022. Review: What have we learned about the effects of heat stress on the pig industry? Animal 16:100349. DOI: https://doi.org/10.1016/j.animal.2021.100349
  16. Liu L, Ren M, Ren K, Jin Y, Yan M, 2020. Heat stress impacts on broiler performance: a systematic review and meta-analysis. Poult Sci 99:6205-6211. DOI: https://doi.org/10.1016/j.psj.2020.08.019
  17. Lundberg SM, Lee SI, 2017. A unified approach to interpreting model predictions. Proc. 31st Conf. Neural Information Processing Systems (NIPS2017), Long Beach. Available from: https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf
  18. M’Hamdi N, Darej C, Attia K, El Akram Znaidi I, Khattab R, Djelailia H, et al., 2021. Modelling THI effects on milk production and lactation curve parameters of Holstein dairy cows. J Therm Biol 99:102917. DOI: https://doi.org/10.1016/j.jtherbio.2021.102917
  19. Machado MR, Karray S, De Sousa IT, 2019. LightGBM: An effective decision tree gradient boosting method to predict customer loyalty in the finance industry. Proc. 14th Int. Conf. Comput. Sci. Educ. (ICCSE), Toronto; pp. 1111–1116. DOI: https://doi.org/10.1109/ICCSE.2019.8845529
  20. Mueller R, Behrendt T, Hammer A, Kemper A, 2012. A new algorithm for the satellite-based retrieval of solar surface irradiance in spectral bands. Remote Sens 4:622-647. DOI: https://doi.org/10.3390/rs4030622
  21. Niu K, Zhong J, Hu X, 2024. Impacts of climate change-induced heat stress on pig productivity in China. Sci Total Environ 908:168215. DOI: https://doi.org/10.1016/j.scitotenv.2023.168215
  22. Park T, Lee J, Oh H, Yun WJ, Lee KW, 2025. Optimizing indoor farm monitoring efficiency using UAV: yield estimation in a GNSS-denied cherry tomato greenhouse. arXiv:2505.00995.
  23. Patrick B, Johnson T, Kanjo E, 2024. Internetless low-cost sensing system for real-time livestock monitoring. IEEE Sensors Lett 8:7500504. DOI: https://doi.org/10.1109/LSENS.2024.3399884
  24. Perez R, Ineichen P, Moore K, Kmiecik M, Chain C, George R, Vignola F, 2002. A new operational model for satellite-derived irradiances: Description and validation. Sol Energy 73:307-317. DOI: https://doi.org/10.1016/S0038-092X(02)00122-6
  25. Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A, 2018. Catboost: Unbiased boosting with categorical features. Proc. 32nd Conf. Neural Information Processing Systems (NIPS2018), Montreal. Available from: https://proceedings.neurips.cc/paper_files/paper/2018/file/14491b756b3a51daac41c24863285549-Paper.pdf
  26. Rajagukguk RA, Ramadhan RAA, Lee HJ, 2020. A review on deep learning models for forecasting time series data of solar Irradiance and photovoltaic power. Energies 13:6623. DOI: https://doi.org/10.3390/en13246623
  27. Soci C, Hersbach H, Simmons A, Poli P, Bell B, Berrisford P, et al., 2024. The ERA5 global reanalysis from 1940 to 2022. Q J R Meteorol Soc 150:4014–4048. DOI: https://doi.org/10.1002/qj.4803
  28. Stein JS, Holmgren WF, Forbess J, Hansen CW, 2016. PVLIB: Open source photovoltaic performance modeling functions for Matlab and Python. Proc. IEEE 43rd Photovoltaic Specialists Conference (PVSC), Portland. pp. 3425-3430. DOI: https://doi.org/10.1109/PVSC.2016.7750303
  29. Uea-Anuwong T, Lam YK, Yau D, Li CM, Xin C, Paudel S, et al., 2025. Impact of temperature-humidity index on heat stress behavior and welfare of battery-caged yellow-feathered native broilers during summertime in Hong Kong: An observational study. J Therm Biol 132:104224. DOI: https://doi.org/10.1016/j.jtherbio.2025.104224
  30. Wan Q, Smigaj M, Brede B, Kooistra L, 2024. Optimizing UAV-based uncooled thermal cameras in field conditions for precision agriculture. Int J Appl Earth Obs Geoinf 134:104184. DOI: https://doi.org/10.1016/j.jag.2024.104184
  31. Yan G, Shi Z, Cui B, Li H, 2022. Developing a new thermal comfort prediction model and web-based application for heat stress assessment in dairy cows. Biosyst Eng 214:72-89. DOI: https://doi.org/10.1016/j.biosystemseng.2021.12.006
  32. Yang D, Gu Y, Mayer MJ, Gueymard CA, Wang W, Kleissl J, et al., 2024. Regime-dependent 1-min irradiance separation model with climatology clustering. Renew Sustain Energy Rev 189:113992. DOI: https://doi.org/10.1016/j.rser.2023.113992
  33. Yu P, Zhao T, Shi J, Ran Y, Jia L, Ji D, Xue H, 2022. Global spatiotemporally continuous MODIS land surface temperature dataset. Sci Data 9:143. DOI: https://doi.org/10.1038/s41597-022-01214-8

Metrics

Citations and online attention from Dimensions, Altmetric and PlumX.

PlumX Metrics

License

Copyright (c) 2026 the Author(s)

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

PAGEPress has chosen to apply the Creative Commons Attribution NonCommercial 4.0 International License (CC BY-NC 4.0) to all manuscripts to be published.