Techniques for Development of Swine Performance Response Surfaces

The NC204 swine growth model (NCPIG) was used to generate pig physiological response data for a range of environmental variables during growth (20 to 110 kg). These response data were then used to successfully train and validate three backward propagation neural network models describing the effect of environment on average daily gain, feed intake, heat production (total and fraction sensible), and physiological status of the animal. A generalization stage was conducted in which predictions from NCPIG using actual weather data were compared to those found by the neural network models for the same environmental inputs. The neural network models were generally able to follow selected animal response variables predicted from NCPIG, although average daily gain and daily feed intake exhibited occasional large deviations during the generalization phase, suggesting further training and validation are needed. The technique developed in this article shows how neural network models can be used to simplify data extraction from a complex model such as NCPIG by fitting neural networks to a few fundamental input relations based on carefully chosen numerical experiments. The simpler neural networks are then appropriate in instances where use of the full model is difficult or impossible, provided that parameters such as genotype and feed ration used for network training are maintained.