Jump to Main Content
Prediction of carbon dioxide concentration in weaned piglet buildings by wavelet neural network models
- Besteiro, Roberto, Arango, Tamara, Ortega, J. Antonio, Rodríguez, M. Ramiro, Fernández, M. Dolores, Velo, Ramón
- Computers and electronics in agriculture 2017 v.143 pp. 201-207
- air, air quality, animal welfare, buildings, carbon dioxide, environmental factors, farms, neural networks, piglets, prediction, temperature, wavelet, weanlings
- Carbon dioxide concentration is a major factor in air quality, animal welfare and air exchange rates inside livestock buildings. CO2 concentration series show a dynamic, non-linear and non-stationary behavior. This type of process can be handled by Wavelet Neural Network (WNN) models, which have been developed in recent years. The purpose of this paper is to develop WNN models capable of predicting the dynamics of CO2 in weaner buildings.Outdoor temperatures, CO2 concentration and temperature in the animal zone and animal activity were recorded in a commercial piglet farm during two complete production cycles. Two WNN models were generated from the recorded data: an autoregressive model (AM) that used the CO2 series and outdoor temperatures for the prediction, and an explanatory model (EM) that used only exogenous variables, namely outdoor temperature, temperature in the animal zone and animal activity.Because CO2 is a highly autoregressive variable, the best results are obtained with the AM. The AM yield an RMSE of 26.330 ppm and a Pearson’s r of 0.995. The EM, with an RMSE of 154.361 ppm and a Pearson’s r of 0.895, reveal the importance of indoor and outdoor temperatures and, consequently, of ventilation rate, for CO2 concentration inside the building. In addition, our results show the effects of animal activity on CO2 concentration, which are delayed by 40–50 min. Based on these results, the CO2 concentrations in the animal zone of weaner buildings can be accurately predicted by WNN models. Therefore, WNN modeling could be widely used to predict and understand the dynamics of environmental variables inside livestock buildings.