Abstract

The increasing frequency of heatwaves and high-temperature events due to climate change intensifies heat stress and mortality risk in broiler production and necessitates reassessment of facility design and energy management. This study developed a machine learning surrogate model trained on BES-simulated heating and cooling loads to estimate future energy load changes in broiler houses under SSP climate scenarios. Training data were constructed using simulated energy load results under different insulation conditions combined with historical meteorological data (2011–2020). Four machine learning models, namely Linear Regression, Random Forest, Gradient Boosting, and XGBoost, were applied to compare their predictive performance for heating and cooling loads. Model performance was evaluated using five-fold cross-validation (K-fold cross-validation, K = 5). XGBoost and Random Forest showed the best performance for heating and cooling load prediction, respectively (R2 > 0.99, MAPE < 10%). These models were applied to SSP1-2.6 and SSP5-8.5 climate scenarios. Results showed decreasing heating loads and increasing cooling loads across all scenarios, with cooling demand projected to increase by more than 150% relative to baseline levels under SSP5-8.5 by the late 21st century. This study demonstrates that simulation-trained machine learning can efficiently estimate long-term energy-demand changes, supporting climate-responsive facility design and energy management in livestock housing.

IPC Classification

Keywords