With the rising temperatures and humidity, the frequency and intensity of heat stress is affecting the productivity, animal welfare and profitability of farms. Environmental conditions are traditionally described by the temperature–humidity index (THI) and this index do not fully describe the physiological responses of the individual. Rectal thermometry, on the other hand, is a good reference measurement, but it is invasive, time consuming, and not suitable for continuous monitoring of a herd. The present study aims to propose a framework for infrared thermography (IRT) for non-invasive assessment of heat stresses in dairy cattle based on radiometric correction, automated body segmentation, region-of-interest (ROI) detection, thermal feature extraction, and machine-learning classification, and to integrate the barn microclimate measurements into this framework. The framework was tested with 120 animal-sessions ranging between THI 65.8 to 89.6. The overall performance of Otsu based Segmentation was good in extracting the animal regions, with an intersection-over-union (IoU) score of 0.95. The maximum eye temperature had a high correlation with the rectal temperature (r = 0.92) and RMSE of 0.15 °C. The logistic regression classifier that integrated eye temperature and THI had an accuracy of 0.84 and an area under the receiver operating characteristic curve (AUC) of 0.92 to identify heat stressed animals based on the criterion of rectal temperature ≥ 39.2 °C. The benefit of adding animal level thermal information was demonstrated by comparing with THI-only classification that had an AUC of 0.75. In addition, a 24-hour monitoring system detected an average delay of 2.25 hours between changes in THI and change in herd eye-temperature. This temporal relationship can be used to make pre-emptive cooling decisions. The proposed framework provides multiple levels of alerts for shade, sprinkler and ventilation management, providing a practical way to improve climate resilient livestock production, animal welfare and even resource utilisation.
M. G. Ciliberti, M. Albenzio, and A. Sevi, “From Sensors to Sustainability: Integrating Welfare, Management, and Climate Resilience in Small Ruminant Farm Systems,” Animals, vol. 15, no. 22, p. 3240, Nov. 2025, doi: 10.3390/ani15223240.
A. P. Nugroho et al., “Development of a low-cost thermal imaging system for water stress monitoring in indoor farming,” Smart Agricultural Technology, vol. 11, p. 101048, Aug. 2025, doi: 10.1016/j.atech.2025.101048.
A. I. Hazmy et al., “Potential of Satellite-Airborne Sensing Technologies for Agriculture 4.0 and Climate-Resilient: A Review,” IEEE Sensors Journal, vol. 24, no. 4, pp. 4161–4180, Feb. 2024, doi: 10.1109/jsen.2023.3343428.
S. Kundu, D. K. Saini, R. K. Meena, R. N. Bahuguna, and S. V. K. Jagadish, “High-throughput phenotyping and AI technologies for deciphering crop resilience to heat stress,” Plant Physiology Reports, vol. 29, no. 4, pp. 699–715, Nov. 2024, doi: 10.1007/s40502-024-00821-4.
M. Awais et al., “UAV-based remote sensing in plant stress imagine using high-resolution thermal sensor for digital agriculture practices: a meta-review,” International Journal of Environmental Science and Technology, vol. 20, no. 1, pp. 1135–1152, Jan. 2022, doi: 10.1007/s13762-021-03801-5.
M. Smigaj et al., “Thermal Infrared Remote Sensing of Stress Responses in Forest Environments: a Review of Developments, Challenges, and Opportunities,” Current Forestry Reports, vol. 10, no. 1, pp. 56–76, Dec. 2023, doi: 10.1007/s40725-023-00207-z.
E. B. Rebez, V. Sejian, M. V. Silpa, and F. R. Dunshea, “Heat Stress and Histopathological Changes of Vital Organs: A Novel Approach to Assess Climate Resilience in Farm Animals,” Sustainability, vol. 15, no. 2, p. 1242, Jan. 2023, doi: 10.3390/su15021242.
A. Noman Mahin, N. Adnan, and R. Khondoker, “Precision Agriculture using Machine Learning and Deep Learning Algorithms: A Comprehensive Study,” Journal of Agriculture & Education Research, vol. 04, no. 01, pp. 01–29, Jan. 2026, doi: 10.64030/3065-8764.04.01.01.
E. Rebez et al., “Applications of Artificial Intelligence for Heat Stress Management in Ruminant Livestock,” Sensors, vol. 24, no. 18, p. 5890, Sep. 2024, doi: 10.3390/s24185890.
V. Sejian, C. G. Shashank, M. V. Silpa, A. P. Madhusoodan, C. Devaraj, and S. Koenig, “Non-Invasive Methods of Quantifying Heat Stress Response in Farm Animals with Special Reference to Dairy Cattle,” Atmosphere, vol. 13, no. 10, p. 1642, Oct. 2022, doi: 10.3390/atmos13101642.
W. Ashfaq, G. Brodie, S. Fuentes, and D. Gupta, “Infrared Thermal Imaging and Morpho-Physiological Indices Used for Wheat Genotypes Screening under Drought and Heat Stress,” Plants, vol. 11, no. 23, p. 3269, Nov. 2022, doi: 10.3390/plants11233269.
M. D. Ghezzi et al., “Utilization of Infrared Thermography in Assessing Thermal Responses of Farm Animals under Heat Stress,” Animals, vol. 14, no. 4, p. 616, Feb. 2024, doi: 10.3390/ani14040616.
C. Kaya, “Metabolomics-guided engineering of drought-resilient crops: Integrating multi-omics and AI for climate-smart agriculture,” Plant Science, vol. 365, p. 113025, Apr. 2026, doi: 10.1016/j.plantsci.2026.113025.
H. T. Nguyen et al., “Advancing Crop Resilience Through High-Throughput Phenotyping for Crop Improvement in the Face of Climate Change,” Plants, vol. 14, no. 6, p. 907, Mar. 2025, doi: 10.3390/plants14060907.
A. Joy et al., “Non-invasive measure of heat stress in sheep using machine learning techniques and infrared thermography,” Small Ruminant Research, vol. 207, p. 106592, Feb. 2022, doi: 10.1016/j.smallrumres.2021.106592.
Rehman, Z. Ahmad, M. Ramakrishnan, R. Kalendar, and Q. Zhuge, “Regulation of plant epigenetic memory in response to cold and heat stress: towards climate resilient agriculture,” Functional & Integrative Genomics, vol. 23, no. 4, Sep. 2023, doi: 10.1007/s10142-023-01219-5.
CRediT Author Statement
The author reviewed the results and approved the final version of the manuscript.
Acknowledgements
The authors acknowledge the valuable guidance and encouragement received from their research supervisors.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics Declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of Data and Materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author Information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding Author
Zengling Wang
Agricultural Engineering, College of Engineering, China Agricultural University, Beijing 100083, China.
This license permits unrestricted use, sharing, distribution, reproduction, and adaptation in any medium or format, including for commercial purposes, provided that appropriate credit is given to the original author(s) and the source, a link to the license is provided, and any changes made are indicated.
Zengling Wang, “Thermal Imaging Based Assessment of Livestock Heat Stress for Climate Resilient Farm Management”, Journal of Smart and Sustainable Farming, pp. 139-149, 2026, doi: 10.64026/JSSF/2026012.