Effects of Molasses-Urea Supplementation on Weight Gain,Ruminal Fermentation and Major Microbe Populations of Winter-Grazing Sheep in Inner Mongolia

The present experiment was conducted to determine the effects of Molasses-Urea Supplementation （MUS） on weight gain, ruminal fermentation and major microbial populations in sheep on a winter grazing regime in Inner Mongolia. Total 40 sheep, allowed free consumption of MUS after grazing, served as a treatment group, while 30 sheep, fed only by pasture grazing, served as a control group. Ruminal fermentation parameters, consisted of pH, Bacterial Crude Protein （BCP） and ammonia nitrogen （NH3-N） were measured. In addition, numbers of five symbiotic bacteria were investigated. The results showed as follows： the average daily weight gain, concentration of NH3-N and numbers of protozoa were significantly higher （p〈0.05） in the treatment group than those in the control group. Contrastingly, no significant difference was found in BCP concentration and pH between the two groups. At the end of the experiment, the populations of Selenomonas ruminantium, Anaerovibrio lipolytica, Fibrobacter succinogenes, Ruminococcus flaveciens and Ruminococcus albus in the treatment group were significantly higher than those of the control group （p〈0.05）. These results demonstrated that greater weight gain could be induced during winter in Inner Mongolia by improved nutritional status through promotion of microbial populations using urea and sugar.

Estimation of herbage intake and digestibility of grazing sheep in Zhenglan Banner of Inner Mongolia by using n-alkanes

To reveal the seasonal dynamics of herbage intake, diet composition and digestibility and clarify the relationship of those with herbage nutrient and botanical composition of grazing sheep in Zhenglan Banner of Inner Mongolia, the n-alkane technique was used to test in sheep grazed during June, August and December. The results showed that the sheep mainly ate Fringed sagebrush, Stipa krylovii and Carex in proportions of 33.5,17.9 and 21.2%, respectively, in spring. In summer, the sheep consumed cleistogenes,Potentilla tanacetifolia, Thyme, etc; the intake of Fringed sagebrush, Carex and Stipa declined. In winter,Fringed sagebrush accounted for 50.1% of herbage intake, and the intakes of Cleistogenes and Stipa krylovii increased to 15.3 and 18.4%, respectively. Herbage intake by the sheep in spring was 1.8 kg DM/d, and digestibility was 71.4%. Herbage intake and digestibility decreased slightly to 1.7 kg DM/d and 68.4%during the summer, respectively and decreased significantly to 1.2 kg DM/d and 36.4% in winter. There were significant correlations between diet composition and CP content in winter, diet composition and botanical composition in summer. A highly positive correlation between herbage intake and digestibility was observed in grazing sheep.

Deep learning based classification of sheep behaviour from accelerometer data with imbalance

Classification of sheep behaviour from a sequence of tri-axial accelerometer data has the potential to enhance sheep management.Sheep behaviour is inherently imbalanced(e.g.,more ruminating than walking)resulting in underperforming classification for the minority activities which hold importance.Existing works have not addressed class imbalance and use traditional machine learning techniques,e.g.,Random Forest(RF).We investigated Deep Learning(DL)models,namely,Long Short Term Memory(LSTM)and Bidirectional LSTM(BLSTM),appropriate for sequential data,from imbalanced data.Two data sets were collected in normal grazing conditions using jaw-mounted and earmounted sensors.Novel to this study,alongside typical single classes,e.g.,walking,depending on the behaviours,data samples were labelled with compound classes,e.g.,walking_-grazing.The number of steps a sheep performed in the observed 10 s time window was also recorded and incorporated in the models.We designed several multi-class classification studies with imbalance being addressed using synthetic data.DL models achieved superior performance to traditional ML models,especially with augmented data(e.g.,4-Class+Steps:LSTM 88.0%,RF 82.5%).DL methods showed superior generalisability on unseen sheep(i.e.,F1-score:BLSTM 0.84,LSTM 0.83,RF 0.65).LSTM,BLSTM and RF achieved sub-millisecond average inference time,making them suitable for real-time applications.The results demonstrate the effectiveness of DL models for sheep behaviour classification in grazing conditions.The results also demonstrate the DL techniques can generalise across different sheep.The study presents a strong foundation of the development of such models for real-time animal monitoring.

With Llamas on Guard, Sheep May Safely Graze

Coyotes love to eat lamb. So do stray dogs. Together they cost U. S. sheep farmers more than 20 million dollars in 1990 alone. Many farmers use trained dogs as guards, but accidents reduce their average life span to just