Tanya M. Tebcherani , Philip T. Koshute , Daniel C. Hooper , Megan B. Toms , Rekha S. Holtry
{"title":"Estimating military working dog core temperature change with machine learning: A simulation study","authors":"Tanya M. Tebcherani , Philip T. Koshute , Daniel C. Hooper , Megan B. Toms , Rekha S. Holtry","doi":"10.1016/j.jtherbio.2025.104211","DOIUrl":null,"url":null,"abstract":"<div><div>Military working dogs play a critical role in supporting the United States Military across various missions. Many missions occur in hot environments and predispose military working dogs to hyperthermia, a leading cause of their death. A previous effort created a physics-based model to estimate military working dog core temperature change based on dog attributes, metabolic activity, and environmental conditions. We hypothesize that a machine learning model that builds on the physics-based model may offer additional and complementary benefits. This includes the ability to infer relationships from real-world data, easy modification of features, and compatibility with existing techniques to explain predictions. These benefits would enhance model usability and applicability, especially for scenarios where dogs’ core temperature change patterns may be atypical. As a first step towards a machine learning-based modeling framework, we approximated the physics-based model with three machine learning models, showing feasibility of applying machine learning to this type of data. Of these models, the random forest model, which we dub the “K9-TempML” model, provides the closest core temperature change estimates to the physics-based model and offers well-established methods for feature analyses. We performed feature analysis and augmentation studies on this model to determine the impact of each feature on core temperature change estimates, demonstrating that removing features that are difficult to collect could retain model accuracy but improve usability. Future work includes training a machine learning-based model using real-world data, applying the model to individual military working dogs, and integrating the model into a real-time core temperature change estimation tool and pre-deployment planning aid.</div></div>","PeriodicalId":17428,"journal":{"name":"Journal of thermal biology","volume":"131 ","pages":"Article 104211"},"PeriodicalIF":2.9000,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of thermal biology","FirstCategoryId":"99","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0306456525001688","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Military working dogs play a critical role in supporting the United States Military across various missions. Many missions occur in hot environments and predispose military working dogs to hyperthermia, a leading cause of their death. A previous effort created a physics-based model to estimate military working dog core temperature change based on dog attributes, metabolic activity, and environmental conditions. We hypothesize that a machine learning model that builds on the physics-based model may offer additional and complementary benefits. This includes the ability to infer relationships from real-world data, easy modification of features, and compatibility with existing techniques to explain predictions. These benefits would enhance model usability and applicability, especially for scenarios where dogs’ core temperature change patterns may be atypical. As a first step towards a machine learning-based modeling framework, we approximated the physics-based model with three machine learning models, showing feasibility of applying machine learning to this type of data. Of these models, the random forest model, which we dub the “K9-TempML” model, provides the closest core temperature change estimates to the physics-based model and offers well-established methods for feature analyses. We performed feature analysis and augmentation studies on this model to determine the impact of each feature on core temperature change estimates, demonstrating that removing features that are difficult to collect could retain model accuracy but improve usability. Future work includes training a machine learning-based model using real-world data, applying the model to individual military working dogs, and integrating the model into a real-time core temperature change estimation tool and pre-deployment planning aid.
期刊介绍:
The Journal of Thermal Biology publishes articles that advance our knowledge on the ways and mechanisms through which temperature affects man and animals. This includes studies of their responses to these effects and on the ecological consequences. Directly relevant to this theme are:
• The mechanisms of thermal limitation, heat and cold injury, and the resistance of organisms to extremes of temperature
• The mechanisms involved in acclimation, acclimatization and evolutionary adaptation to temperature
• Mechanisms underlying the patterns of hibernation, torpor, dormancy, aestivation and diapause
• Effects of temperature on reproduction and development, growth, ageing and life-span
• Studies on modelling heat transfer between organisms and their environment
• The contributions of temperature to effects of climate change on animal species and man
• Studies of conservation biology and physiology related to temperature
• Behavioural and physiological regulation of body temperature including its pathophysiology and fever
• Medical applications of hypo- and hyperthermia
Article types:
• Original articles
• Review articles