Machine learning algorithms for predicting peak yield in buffaloes using linear traits

Abstract

Various studies have proved that linear traits have strong relationship with milk productivity but no such models are available for selection of animals based on linear traits. The present study conducted during 2020-22, is an attempt to develop an intelligent model using machine learning algorithms to predict peak milk yield based on its linear traits for selection of best dairy animals. A dataset on 14 linear traits of 259 buffalos across 5 lactations with peak milk yield was created and used for developing models. Data was collected from the buffalos having 8 to 26 kg peak milk yield maintained at Animal Farm Section, Central Institute for Research on Buffaloes, Hisar and also from private farms maintained by farmers. Predictive models were developed using various machine learning algorithms (artificial neural network, support vector regression and random forest) along with multi-linear regression executed on WEKA machine learning platform. Performance of these models was evaluated using evaluation metrics root mean squared error (RMSE). Results revealed that the Artificial Neural Network (ANN) model performed best with minimum RMSE 2.0308. Rear udder height and Lactation number emerged as the two most important attributes affecting the peak milk yield. Such model will be useful and handy for the stakeholders in selection of best dairy animals based on linear traits in absence of authentic record of peak milk yield.

Keywords

• Buffalo, Dairy, Linear traits, Machine learning algorithms, Selection