🤖 AI Summary
This study addresses increasing volatility in Italian honey yields exacerbated by climate change, developing a tree-based predictive system integrating hive observational data with high-resolution meteorological variables to elucidate climate-driven mechanisms affecting foraging activity. It presents the first systematic evaluation of XGBoost and Random Forest models in this domain, assessing both interpretability and robustness, and proposes a cross-model-family ensemble strategy (stacking and blending) to enhance prediction stability. Experimental results show the optimal tree model reduces mean absolute error (MAE) by 32% relative to a linear regression baseline. SHAP-based interpretability analysis identifies accumulated temperature, precipitation variability, and phenological overlap between bloom periods and foraging seasons as the three dominant drivers. The framework supports evidence-based apicultural risk management and actuarial design of climate-indexed honey yield insurance products.
📝 Abstract
The beekeeping sector has experienced significant production fluctuations in recent years, largely due to increasingly frequent adverse weather events linked to climate change. These events can severely affect the environment, reducing its suitability for bee activity. We conduct a forecasting analysis of honey production across Italy using a range of machine learning models, with a particular focus on weather-related variables as key predictors. Our analysis relies on a dataset collected in 2022, which combines hive-level observations with detailed weather data. We train and compare several linear and nonlinear models, evaluating both their predictive accuracy and interpretability. By examining model explanations, we identify the main drivers of honey production. We also ensemble models from different families to assess whether combining predictions improves forecast accuracy. These insights support beekeepers in managing production risks and may inform the development of insurance products against unexpected losses due to poor harvests.
