Evaluation of a Binary Classification Approach to Detect Herbage Scarcity Based on Behavioral Responses of Grazing Dairy Cows.

Leonie Hart,Uta Dickhoefer,Christina Umstaetter,Esther Paulenz

doi:10.3390/s22030968

Leonie Hart, Uta Dickhoefer + Show 2 more

Open Access

https://doi.org/10.3390/s22030968

Copy DOI

Abstract

In precision grazing, pasture allocation decisions are made continuously to ensure demand-based feed allowance and efficient grassland utilization. The aim of this study was to evaluate existing prediction models that determine feed scarcity based on changes in dairy cow behavior. During a practice-oriented experiment, two groups of 10 cows each grazed separate paddocks in half-days in six six-day grazing cycles. The allocated grazing areas provided 20% less feed than the total dry matter requirement of the animals for each entire grazing cycle. All cows were equipped with noseband sensors and pedometers to record their head, jaw, and leg activity. Eight behavioral variables were used to classify herbage sufficiency or scarcity using a generalized linear model and a random forest model. Both predictions were compared to two individual-animal and day-specific reference indicators for feed scarcity: reduced milk yields and rumen fill scores that undercut normal variation. The predictive performance of the models was low. The two behavioral variables “daily rumination chews” and “bite frequency” were confirmed as suitable predictors, the latter being particularly sensitive when new feed allocation is present in the grazing set-up within 24 h. Important aspects were identified to be considered if the modeling approach is to be followed up.

Highlights

Current sensor technology in farming offers decision support in addition to the farmer’s knowledge and experience
We identified three key points which can be put into context for further model development as follows: Firstly, the bite frequency and the daily number of rumination chews are confirmed to be important variables, as already identified by Shafiullah et al [19]
There is potential for some of the behavioral predictors to indicate herbage scarcity and to further develop this approach according to different grazing set-ups

Summary

Introduction

Current sensor technology in farming offers decision support in addition to the farmer’s knowledge and experience. Binary systems indicate need or no need for action, thereby enabling farm staff to respond to crop and animal reactions in a timely manner. Many precision technologies have already been adopted; the implementation of such in the livestock sector is hugely important, as it can improve consumer trust and product traceability [1]. Sensor data gathered in livestock farming play a growing role for proactive, instead of reactive, management to improve animal production, health, and welfare [1,2,3]. Predictions on an individual animal basis that consider physiological evolvements over time and might even combine information of various sensors may have the advantage of detecting vulnerabilities in large herds before it is possible for humans, but they generate large amounts of data, which calls for machine learning approaches [4,5]

Objectives

Methods

Results

Discussion

Conclusion