Construction of a statistical learning tool based on ordinary differential equations to model the digestive behaviour of ross chickens

Nicolas Bloyet; Hélène Flourent; Emmanuel Frénod; Marouan Handa; Harold Moundoyi; Thuy Vo Thi Phuong

doi:10.1051/proc/202067005

Geodesic

Parcourir par

Construction of a statistical learning tool based on ordinary differential equations to model the digestive behaviour of ross chickens

Nicolas Bloyet ^1,² ; Hélène Flourent ² ; Emmanuel Frénod ^2,¹ ; Marouan Handa ³ ; Harold Moundoyi ⁴ ; Thuy Vo Thi Phuong ⁵

¹ See-d, 6, rue Henri Becquerel -CP 101, 56038 Vannes Cedex, France
² Université Bretagne Sud, Laboratoire de Mathématiques de Bretagne Atlantique,UMR CNRS 6205, Campus de Tohannic, Vannes, France
³ Université de Picardie Jules Verne, LAMFA UMR 7352, 33 Rue St Leu, 80000 Amiens, France
⁴ Sorbonne Université, PR UPMC, Laboratoire de Biologie Intégrative des Modèles Marins, Place Georges Teissier, 29680 Roscoff, France
⁵ Universitè Paris 13 -Galilèe Institute -LAGA, 99 avenue Jean-Baptiste Clèment -93430 Villetaneuse, France

ESAIM. Proceedings, Tome 67 (2020), pp. 61-71.

Voir la notice de l'article provenant de la source EDP Sciences

Résumé

Being able to monitor and forecast farm animal performances is a strategic problem in the agronomy industry. We use a Data-Model Coupling approach to build a biomimetic Statistical Learning tool taking into account some aspects of the biological dynamics of the animal body. The objective is to build a tool which is able to assimilate data about daily feed consumption and measured performances.The model encompasses several sub-models corresponding to compartments and permitting to mimic a kinetic process divided into several steps. Each sub-model contains parameters which can be learnt by using an optimization algorithm and data.The goal of the ﬁrst application of the model on ﬁeld data was to simulate and predict the growth of chickens.An experiment was performed during 70 days to collect every day the feed consumption and the weight gain of a male and a female chickens. After the learning of the model parameters, the model shows a very good approximation of the chicken’s weight evolution over time.

DOI : 10.1051/proc/202067005

Affiliations des auteurs :

Nicolas Bloyet ^{1, 2} ; Hélène Flourent ² ; Emmanuel Frénod ^{2, 1} ; Marouan Handa ³ ; Harold Moundoyi ⁴ ; Thuy Vo Thi Phuong ⁵

@article{EP_2020_67_a5,
     author = {Nicolas Bloyet and H\'el\`ene Flourent and Emmanuel Fr\'enod and Marouan Handa and Harold Moundoyi and Thuy Vo Thi Phuong},
     title = {Construction of a statistical learning tool based on ordinary differential equations to model the digestive behaviour of ross chickens},
     journal = {ESAIM. Proceedings},
     pages = {61--71},
     publisher = {mathdoc},
     volume = {67},
     year = {2020},
     doi = {10.1051/proc/202067005},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.1051/proc/202067005/}
}

TY  - JOUR
AU  - Nicolas Bloyet
AU  - Hélène Flourent
AU  - Emmanuel Frénod
AU  - Marouan Handa
AU  - Harold Moundoyi
AU  - Thuy Vo Thi Phuong
TI  - Construction of a statistical learning tool based on ordinary differential equations to model the digestive behaviour of ross chickens
JO  - ESAIM. Proceedings
PY  - 2020
SP  - 61
EP  - 71
VL  - 67
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.1051/proc/202067005/
DO  - 10.1051/proc/202067005
LA  - en
ID  - EP_2020_67_a5
ER  -

%0 Journal Article
%A Nicolas Bloyet
%A Hélène Flourent
%A Emmanuel Frénod
%A Marouan Handa
%A Harold Moundoyi
%A Thuy Vo Thi Phuong
%T Construction of a statistical learning tool based on ordinary differential equations to model the digestive behaviour of ross chickens
%J ESAIM. Proceedings
%D 2020
%P 61-71
%V 67
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.1051/proc/202067005/
%R 10.1051/proc/202067005
%G en
%F EP_2020_67_a5

Nicolas Bloyet; Hélène Flourent; Emmanuel Frénod; Marouan Handa; Harold Moundoyi; Thuy Vo Thi Phuong. Construction of a statistical learning tool based on ordinary differential equations to model the digestive behaviour of ross chickens. ESAIM. Proceedings, Tome 67 (2020), pp. 61-71. doi : 10.1051/proc/202067005. http://geodesic.mathdoc.fr/articles/10.1051/proc/202067005/

Cité par Sources :