Machine Learning Based Prediction of Insufficient Herbage Allowance with Automated Feeding Behaviour and Activity Data

Sensors

Lorenzo Leso¹  AbuZar Shafiullah²  Jessica Werner³  Bernadette O’Brien⁴  Emer Kennedy⁵  Christina Umstätter⁵ 

[1] Grassland Research and Innovation Centre, Moorepark, Fermoy, Co. Cork P61 C996, Ireland;Agroscope, Tanikon 1, 8356 Ettenhausen, Switzerland;Animal Nutrition and Rangeland Management in the Tropics and Subtropics, University of Hohenheim, 70599 Stuttgart, Germany;Department of Agricultural, Food and Forestry Systems, University of Florence, 50145 Firenze, Italy;;Teagasc, Animal &

关键词: machine learning;    binary classification;    herbage allowance;    feeding behaviour and activities;    precision pasture management;   

DOI  :  10.3390/s19204479

来源: DOAJ

【 摘 要 】

Sensor technologies that measure grazing and ruminating behaviour as well as physical activities of individual cows are intended to be included in precision pasture management. One of the advantages of sensor data is they can be analysed to support farmers in many decision-making processes. This article thus considers the performance of a set of RumiWatchSystem recorded variables in the prediction of insufficient herbage allowance for spring calving dairy cows. Several commonly used models in machine learning (ML) were applied to the binary classification problem, i.e., sufficient or insufficient herbage allowance, and the predictive performance was compared based on the classification evaluation metrics. Most of the ML models and generalised linear model (GLM) performed similarly in leave-out-one-animal (LOOA) approach to validation studies. However, cross validation (CV) studies, where a portion of features in the test and training data resulted from the same cows, revealed that support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGBoost) performed relatively better than other candidate models. In general, these ML models attained 88% AUC (area under receiver operating characteristic curve) and around 80% sensitivity, specificity, accuracy, precision and F-score. This study further identified that number of rumination chews per day and grazing bites per minute were the most important predictors and examined the marginal effects of the variables on model prediction towards a decision support system.

【 授权许可】

Unknown