Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Real-time grower-finisher pigs’ growth monitored and forecasted using a dynamic linear regression model

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  10th International Livestock Environment Symposium (ILES X)  .(doi:10.13031/iles.18-133)
Authors:   Alberto Peña Fernández, Tomas Norton, Erik Vranken, Daniel Berckmans
Keywords:   Fatteners, feed, forecasting, weight

Abstract. Feed is the largest item cost in pig production, constituting around 70% of the total cost of growing a pig. Over the last years there has been an increase of the costs of feed ingredients while the market price for pig meat has remained the same, making the situation critical for farmers. Today‘s feeding strategies at commercial farms are set at group level according with the needs of the most demanding pig. The aim of this work is to show the potential of monitoring and forecasting feed consumption and weight development of grower-finisher pigs at individual level to develop individual feeding strategies.

In this preliminary work, 14 pigs housed in a pen of 16 m2 equipped with two feeding stations supplying two types of feed were studied. Both, Transfer Function and Dynamic Linear Regression modelling approaches were applied to the feed consumption and weight time-series of each individual pig to monitor and forecast the level of response in the pigs to the different changes in feed amount and/or composition, respectively. On average, the TF model fitting agreement is 99% and the Mean Relative Prediction Error of applying the DLR approach with a window size of four days and a forecasting horizon of one day is 1.35%. These properties allow to establish the point in time when a change in the performance of a pig takes place along the growing-finishing phase, allowing to determine set points for design of feeding strategies at individual level.

(Download PDF)    (Export to EndNotes)