RESUMEN
The aim of this Research Communication was to apply the data mining technique to classify which environmental factors have the potential to motivate dairy cows to access natural shade. We defined two different areas at the silvopastoral system: shaded and sunny. Environmental factors and the frequency that dairy cows used each area were measured during four days, for 8 h each day. The shaded areas were the most used by dairy cows and presented the lowest mean values of all environmental factors. Solar radiation was the environmental factor with most potential to classify the dairy cow's decision to access shaded areas. Data mining is a machine learning technique with great potential to characterize the influence of the thermal environment in the cows' decision at the pasture.
Asunto(s)
Conducta Animal/fisiología , Bovinos/psicología , Industria Lechera/métodos , Ambiente , Motivación/fisiología , Luz Solar , Animales , Bovinos/fisiología , Minería de Datos , Femenino , CalorRESUMEN
Lying behavior is an important indicator of the cows' welfare and health. In this study, we evaluate the effect of the physical environment on dairy cows' behaviors raised on a silvopastoral system through a predictive model. There was a difference (p<0.01) in soil surface temperature (SST) and black globe-humidity index (BGHI) between the shaded and sunny areas of the silvopastoral system. The BGHI was the variable most important to classify the cows' decision to seek shaded or sunny areas, while the soil surface temperature affected the choice for the area to perform the lying behaviors. In order to understand the influence of these parameters on cows' lying behavior, we developed another predictive model relating the SST and BGHI with cows lying at shaded and sunny areas. There was significance (p<0.01) for all model parameters. The odds of cows lying increased by approximately 2% with each degree of SST. In contrast, the probability of the cows lying in the shaded areas was 35% less than in sunny areas. The model developed in this study was efficient in identifying changes in the behavior of dairy cows in relation to physical environment. The BGHI influenced the areas used by cows to performing their standing behavior, while the areas used for lying behavior were influenced by the SST.