Towards a Vectorial Approach to Predict Beef Farm Performance

Francesca Abbona,Mario Giacobini,Leonardo Vanneschi

doi:10.3390/app12031137

Francesca Abbona, Mario Giacobini + Show 1 more

Open Access

https://doi.org/10.3390/app12031137

Copy DOI

Abstract

Accurate livestock management can be achieved by means of predictive models. Critical factors affecting the welfare of intensive beef cattle husbandry systems can be difficult to be detected, and Machine Learning appears as a promising approach to investigate the hundreds of variables and temporal patterns lying in the data. In this article, we explore the use of Genetic Programming (GP) to build a predictive model for the performance of Piemontese beef cattle farms. In particular, we investigate the use of vectorial GP, a recently developed variant of GP, that is particularly suitable to manage data in a vectorial form. The experiments conducted on the data from 2014 to 2018 confirm that vectorial GP can outperform not only the standard version of GP but also a number of state-of-the-art Machine Learning methods, such as k-Nearest Neighbors, Generalized Linear Models, feed-forward Neural Networks, and long- and short-term memory Recurrent Neural Networks, both in terms of accuracy and generalizability. Moreover, the intrinsic ability of GP in performing an automatic feature selection, while generating interpretable predictive models, allows highlighting the main elements influencing the breeding performance.

Highlights

IntroductionIt is increasingly common to monitor animals, for greater accuracy in the quantity and quality of information, to achieve economic and environmental sustainability of farms
A large amount of data are nowadays collected in the livestock sector [1,2,3,4]
We analyzed the predictors encapsulated in the final models by both ST- and VE-Genetic Programming (GP), selected with respect to the performance achieved on the test sets by running the algorithms for 40 generations

Summary

Introduction

It is increasingly common to monitor animals, for greater accuracy in the quantity and quality of information, to achieve economic and environmental sustainability of farms. Rather than making a priori assumptions and following pre-programmed algorithms, ML allows the system to learn from data. This field of research is suitable for the management of large datasets, without assuming too specific nor restrictive hypotheses among data [9]. ML is commonly used to predict livestock issues [7,10], such as time of disease events, risk factors for health conditions, failure to complete a production cycle, as well as the genome of complex traits [11]. Studies have been conducted, based on the application of ML techniques, to model the individual intake of cow feed, optimizing health and fertility, to predict the rumen fermentation pattern from milk fatty acids, which influence the quantity and composition of the milk produced and the sensorial and technological characteristics of the meat [10,12]

Methods

Results

Discussion

Conclusion