Applicability of Machine-Learned Regression Models to Estimate Internal Air Temperature and CO2 Concentration of a Pig House

Abstract

Carbon dioxide (CO2) emissions from the livestock industry are expected to increase. A response strategy for CO2 emission regulations is required for pig production as this industry comprises a large proportion of the livestock industry and it is projected that per capita pork consumption will rise. A CO2 emission response strategy can be established by accurately measuring the CO2 concentrations in pig facilities. Here, we compared and evaluated the performance of three different machine learning (ML) models (ElasticNet, random forest regression (RFR), and support vector regression (SVR)) designed to predict CO2 concentration and internal air temperature (Ti) values in the pig house used to regulate a heating, ventilation, and air conditioning (HVAC) control system. For each ML model, the hyperparameter was optimised and the predictive accuracy was evaluated. The order of predictive accuracy for the ML models was ElasticNet < SVR < RFR. Hence, random forest regression provided superior prediction performance. Based on the test dataset, for Ti prediction by RFR, R2 ≥ 0.848 and the root mean square error (RMSE) and mean absolute error (MAE) were 0.235 °C and 0.160 °C, respectively, whilst for CO2 concentration prediction by RFR, R2 ≥ 0.885 and the RMSE and MAE were 64.39 ppm and ≤ 46.17 ppm, respectively.