Crop and Pasture Science Crop and Pasture Science Society
Plant sciences, sustainable farming systems and food quality
RESEARCH ARTICLE

Use of sensor-determined behaviours to develop algorithms for pasture intake by individual grazing cattle

P. L. Greenwood A B F , D. R. Paull B , J. McNally B , T. Kalinowski B , D. Ebert A , B. Little C , D. V. Smith D , A. Rahman D , P. Valencia E , A. B. Ingham C and G. J. Bishop-Hurley C
+ Author Affiliations
- Author Affiliations

A NSW Department of Primary Industries, Beef Industry Centre, University of New England, Armidale, NSW 2351, Australia.

B CSIRO Agriculture and Food, FD McMaster Research Laboratory Chiswick, Armidale, NSW 2350, Australia.

C CSIRO Agriculture and Food, Queensland Biosciences Precinct, St Lucia, Qld 4067, Australia.

D CSIRO Data61, Sandy Bay, Tas. 7005, Australia.

E CSIRO Data61, Pullenvale, Qld 4069, Australia.

F Corresponding author. Email: paul.greenwood@dpi.nsw.gov.au

Crop and Pasture Science 68(12) 1091-1099 https://doi.org/10.1071/CP16383
Submitted: 18 October 2016  Accepted: 16 March 2017   Published: 13 April 2017

Abstract

Practical and reliable measurement of pasture intake by individual animals will enable improved precision in livestock and pasture management, provide input data for prediction and simulation models, and allow animals to be ranked on grazing efficiency for genetic improvement. In this study, we assessed whether pasture intake of individual grazing cattle could be estimated from time spent exhibiting behaviours as determined from data generated by on-animal sensor devices. Variation in pasture intake was created by providing Angus steers (n = 10, mean ± s.d. liveweight 650 ± 77 kg) with differing amounts of concentrate supplementation during grazing within individual ryegrass plots (≤0.22 ha). Pasture dry matter intake (DMI) for the steers was estimated from the slope (kg DM day–1) of the regression of total pasture DM per plot on intake over an 11-day period. Pasture DM in each plot, commencing with ≤2 t DM ha–1, was determined by using repeatedly calibrated pasture height and electronic rising plate meters. The amounts of time spent grazing, ruminating, walking and resting were determined for the 10 steers by using data from collar-mounted, inertial measurement units and a previously developed, highly accurate, behaviour classification model. An initial pasture intake algorithm was established for time spent grazing: pasture DMI (kg day–1) = –4.13 + 2.325 × hours spent grazing (P = 0.010, r2 = 0.53, RSD = 1.65 kg DM day–1). Intake algorithms require further development, validation and refinement under varying pasture conditions by using sensor devices to determine specific pasture intake behaviours coupled with established methods for measuring pasture characteristics and grazing intake and selectivity.

Additional keywords: accelerometer, acoustic sensor, magnetometer, GPS, herbivores.


References

Benvenutti MA, Pavetti DR, Poppi DP, Gordon IJ, Cangiano CA (2016) Defoliation patterns and their implications for management of vegetative tropical pastures to control intake and diet quality by cattle. Grass and Forage Science 71, 424–436.
Defoliation patterns and their implications for management of vegetative tropical pastures to control intake and diet quality by cattle.CrossRef |

Bishop-Hurley G, Henry D, Smith D, Dutta R, Hills J, Rawnsley R, Hellicar A, Tims G, Morshead A, Rahman A, D’Este C, Shu Y (2014) An investigation of cow feeding behaviour using motion sensors. In ‘Proceedings 2014 IEEE Instrument and Measurement Technology Conference (I2MTC)’. 12–15 May 2014, Montevideo, Uruguay. pp. 1285–1290. (Institute of Electrical and Electronics Engineers: Piscataway, NJ, USA)

Bonnet OJF, Meuret M, Tischler MR, Cezimbra IM, Azambuja JCR, Carvalho PCF (2015) Continuous bite monitoring: a method to assess the foraging dynamics of herbivores in natural grazing conditions. Animal Production Science 55, 339–349.
Continuous bite monitoring: a method to assess the foraging dynamics of herbivores in natural grazing conditions.CrossRef |

Braun U, Zürcher S, Hässig M (2015a) Eating and rumination activity in 10 cows over 10 days. Research in Veterinary Science 101, 196–198.
Eating and rumination activity in 10 cows over 10 days.CrossRef | 1:STN:280:DC%2BC2MfntVaqtg%3D%3D&md5=7d9ff3c088578bdcd9115389a1b3d520CAS |

Braun U, Zürcher S, Hässig M (2015b) Evaluation of eating and rumination behaviour in 300 cows of three different breeds using a noseband pressure sensor. BMC Veterinary Research 11, 231
Evaluation of eating and rumination behaviour in 300 cows of three different breeds using a noseband pressure sensor.CrossRef |

Chacon E, Stobbs TH, Sandland RL (1976) Estimation of herbage consumption using measurements of eating behaviour. Journal of the British Grassland Society 31, 81–87.
Estimation of herbage consumption using measurements of eating behaviour.CrossRef |

Dobos RC, Fulkerson WJ, Sinclair K, Hinch GN (2009) Grazing behaviour and pattern of intake of dairy cows grazing kikuyu (Pennisetum clandestinum) grass pastures in relation to sward height and length of grazing session. Animal Production Science 49, 233–238.
Grazing behaviour and pattern of intake of dairy cows grazing kikuyu (Pennisetum clandestinum) grass pastures in relation to sward height and length of grazing session.CrossRef |

Dutta R, Smith D, Rawnsley R, Bishop-Hurley G, Hills J, Timms G, Henry D (2015) Dynamic cattle behavioural classification using supervised ensemble classifiers. Computers and Electronics in Agriculture 111, 18–28.
Dynamic cattle behavioural classification using supervised ensemble classifiers.CrossRef |

Galli JR, Cangiano CA, Milone DH, Laca EA (2011) Acoustic monitoring of short-term ingestive behaviour and intake in grazing sheep. Livestock Science 140, 32–41.
Acoustic monitoring of short-term ingestive behaviour and intake in grazing sheep.CrossRef |

González LA, Bishop-Hurley G, Handcock RN, Crossman C (2015) Behavioural classification of data from collars containing motion sensors in grazing cattle. Computers and Electronics in Agriculture 110, 91–102.
Behavioural classification of data from collars containing motion sensors in grazing cattle.CrossRef |

Greenwood PL, Bell AW (2014) Consequences of nutrition during gestation, and the challenge to better understand and enhance livestock productivity and efficiency in pastoral ecosystems. Animal Production Science 54, 1109–1118.
Consequences of nutrition during gestation, and the challenge to better understand and enhance livestock productivity and efficiency in pastoral ecosystems.CrossRef |

Greenwood PL, Ingham AB (2015) Livestock behaviour classification workshop. A report from a CSIRO Workshop held under the auspices of the Digital Agriculture initiative. CSIRO Agriculture, Queensland Biosciences Precinct, University of Queensland.

Greenwood PL, Valencia P, Overs L, Paull DP, Purvis IW (2014) New ways of measuring intake, efficiency and behaviour of grazing livestock. Animal Production Science 54, 1796–1804.
New ways of measuring intake, efficiency and behaviour of grazing livestock.CrossRef |

Greenwood PL, Bishop-Hurley GJ, Gonzalez LA, Ingham AB (2016) Development and application of a livestock phenomics platform to enhance productivity and efficiency at pasture. Animal Production Science 56, 1299–1311.
Development and application of a livestock phenomics platform to enhance productivity and efficiency at pasture.CrossRef |

Hawkesford MJ, Lorence A (2017) Plant phenotyping: increasing throughput and precision. Functional Plant Biology 44, v–vii.
Plant phenotyping: increasing throughput and precision.CrossRef |

Lukuyu M, Paull DR, Johns WH, Niemeyer D, McLeod J, McCorkell B, Savage D, Purvis IW, Greenwood PL (2014) Precision of estimating individual feed intake of grazing animals offered low, declining pasture availability. Animal Production Science 54, 2105–2111.
Precision of estimating individual feed intake of grazing animals offered low, declining pasture availability.CrossRef |

Navon S, Mizrach A, Hetzroni A, Ungar ED (2013) Automatic recognition of jaw movements in free ranging cattle, goats and sheep, using acoustic monitoring. Biosystems Engineering 114, 474–483.
Automatic recognition of jaw movements in free ranging cattle, goats and sheep, using acoustic monitoring.CrossRef |

Oudshoorn FW, Cornou C, Hellwing ALF, Hansen HH, Munksgaard L, Lund P, Kristensen T (2013) Estimation of grass intake on pasture for dairy cows using tightly and loosely mounted di- and tri-axial accelerometers. Computers and Electronics in Agriculture 99, 227–235.
Estimation of grass intake on pasture for dairy cows using tightly and loosely mounted di- and tri-axial accelerometers.CrossRef |

Penning PD (Ed.) (2004) ‘Herbage intake handbook.’ (British Grassland Society: Reading, UK)

Rahman A, Smith D, Hills J, Bishop-Hurley G, Henry D, Rawnsley R (2016) A comparison of autoencoder and statistical features for cattle behaviour classification. In ‘IEEE Joint International Conference on Neural Networks (IJCNN)’. 24–29 July 2016, Vancouver, Canada. pp. 2954–2960. (Institute of Electrical and Electronics Engineers Computational Intelligence Society: Piscataway, NJ, USA)

Rombach M, Münger A, Südekum K-H, Schori F (2015) Estimation of individual intake of grazing dairy cows with RumiWatch®. In ‘Proceedings Third DairyCare Conference’. Zadar, Croatia. (Ed. CH Knight) p. 15. (DairyCare COST Action FA1308: Copenhagen, Denmark)

Rook AJ, Harvey A, Parsons AJ, Orr RJ, Rutter SM (2004) Bite dimensions and grazing movements by sheep and cattle grazing homogeneous perennial ryegrass swards. Applied Animal Behaviour Science 88, 227–242.
Bite dimensions and grazing movements by sheep and cattle grazing homogeneous perennial ryegrass swards.CrossRef |

Rutter SM, Champion RA, Penning PD (1997) An automatic system to record foraging behaviour in free-ranging ruminants. Applied Animal Behaviour Science 54, 185–195.
An automatic system to record foraging behaviour in free-ranging ruminants.CrossRef |

Sheahan AJ, Kolver ES, Roche JR (2011) Genetic strain and diet effects on grazing behavior, pasture intake, and milk production. Journal of Dairy Science 94, 3583–3591.
Genetic strain and diet effects on grazing behavior, pasture intake, and milk production.CrossRef | 1:CAS:528:DC%2BC3MXnvFahsb8%3D&md5=3ad9602aa03033a554a2c417ef63f7b7CAS |

Smart AJ, Schacht WH, Pederson JF, Undersander DJ, Moser LE (1998) Prediction of leaf:stem ratio in grasses using near infrared reflectance spectroscopy. Journal of Range Management 51, 447–449.
Prediction of leaf:stem ratio in grasses using near infrared reflectance spectroscopy.CrossRef |

Smith D, Dutta R, Hellicar A, Bishop-Hurley G, Rawnsley R, Henry D, Hills J, Timms G (2015a) Bag of class posteriors, a new multivariate time series classifier applied to animal behaviour identification. Expert Systems with Applications 42, 3774–3784.
Bag of class posteriors, a new multivariate time series classifier applied to animal behaviour identification.CrossRef |

Smith D, Little B, Greenwood PL, Valencia P, Rahman A, Ingham A, Bishop–Hurley G, Shahriar S, Hellicar H (2015b) A study of sensor derived features in cattle behaviour models. In ‘Sensors 2015’. 1–4 November 2015, Busan, South Korea. pp. 1–4. (Institute of Electrical and Electronics Engineers: Piscataway, NJ, USA)

Smith D, Rahman A, Bishop-Hurley G, Hills J, Shahriar S, Henry D, Rawnsley R (2016) Behavior classification of cows fitted with motion collars: Decomposing multi-class classification into a set of binary problems. Computers and Electronics in Agriculture 131, 40–50.
Behavior classification of cows fitted with motion collars: Decomposing multi-class classification into a set of binary problems.CrossRef |

Tani Y, Yokota Y, Yayota M, Ohtani S (2013) Automatic recognition and classification of cattle chewing activity by an acoustic monitoring method with a single-axis accelerometer. Computers and Electronics in Agriculture 92, 54–65.
Automatic recognition and classification of cattle chewing activity by an acoustic monitoring method with a single-axis accelerometer.CrossRef |

Umemura K, Wanaka T, Ueno T (2009) Technical note: Estimation of feed intake while grazing using a wireless system requiring no halter. Journal of Dairy Science 92, 996–1000.
Technical note: Estimation of feed intake while grazing using a wireless system requiring no halter.CrossRef | 1:CAS:528:DC%2BD1MXivVaktL4%3D&md5=8403d6fdd846436644246db77af34ce8CAS |

Wark T, Corke P, Sikka P, Klingbeil L, Guo Y, Crossman C, Valencia P, Swain D, Bishop-Hurley G (2007) Transforming agriculture through pervasive wireless sensor networks. IEEE Pervasive Computing 6, 50–57.
Transforming agriculture through pervasive wireless sensor networks.CrossRef |



Rent Article (via Deepdyve) Export Citation