Enhancing Ammonia Concentration Prediction with a Transfer-Learning-Based Model: Application in a Pig Farm

Globally, the swine industry is a major component of agricultural production, and the increasing scale and intensification of pig farming have heightened concerns about NH₃ emissions. As farms expand and adopt smart farming technologies, there is a need for reliable prediction of NH₃ concentrations without relying solely on costly physical sensors. In this study, we developed an artificial intelligence-based prediction model for NH₃ concentration in commercial pig houses and examined the effects of data collection intervals and learning strategies. We compared a standalone model trained only on local data with a transfer learning model that adapts a pre-trained model to a target farm with limited data. Transfer learning consistently outperformed the standalone approach across all data collection intervals (10, 20, 30 and 60 min). The best-performing Random Forest and XGBoost models achieved a coefficient of determination (<i>R</i>²) of 0.969, root mean square error (<i>RMSE</i>) of about 1.0 ppm and mean absolute percentage error (<i>MAPE</i>) below 5%. These results show that transfer learning can provide accurate NH₃ predictions in swine housing even with sparse data, supporting more sustainable and data-efficient environmental management.