Prediction of drinking water requirements by applying statistical and machine learning models in growing-finishing stage of pigs

Abstract

Effective monitoring and management of drinking water in swine buildings is a crucial aspect for promoting pigs' health and productivity. Therefore, this study aimed to quantify and model drinking water intake (DWI) in growing-finishing pigs by providing them with three concentrated diets in experimental pig barns. Two independent experiments were conducted in three experimental barns between 2021 and 2022. One statistical (multiple linear regression) and four machine learning algorithms (elastic net, random forest regression, support vector regression, and multilayer perceptron) were employed, with feed intake (FI), mass of pigs (MP), pigs' body temperature (PBT), room temperature (RT), CO2 concentration (RCO2), and temperature-humidity index (RTHI) as input parameters. The results revealed that pigs with a body mass of 30 to 60 kg consumed approximately 3.58 L of drinking water and 2.10 kg of concentrated diet per day. Additionally, strong positive correlations were observed between MP, FI, and DWI (correlation coefficient (r) > 90) during both experimental periods. The findings indicated that the random forest regression algorithm performed the best, explaining over 90% and 80% of the observed and predicted data during the training and testing phases, respectively. However, during the testing phase, the multiple linear regression methods performed the worst (R2 < 0.79 and RMSE > 0.89 L pig−1 day−1) when compared to the other models. Sensitivity analysis indicated that among all the variables, MP had the greatest impact on predicting DWI, followed by FI, RCO2, RTHI, and RT. The study concluded that random forest regression could predict DWI precisely, which can assist pig farmers in enhancing their water monitoring capabilities and promptly assessing the availability of drinking water.