Work

Modeling associations between migratory movements and seasonal honey bee colony survival: a machine-learning approach with big data

Year: 2026
Type: article
Abstract: This study investigates relationships between commercial beekeeping practices—particularly colony movement and recorded covariates—and honey bee colony survival. Using data on 362,884 colonies from 62 beekeepers over 4 years (2022–2026), we assessed how movement frequency and timing are associated with observed survival outcomes. Higher transportation frequency was associated with a lower probability of surviving beyond one season, while longer average intervals between moves were associated with higher predicted longevity. Because important drivers of survival (e.g., meteorological conditions, colony health, and floral resources) are not fully measured, these findings should be interpreted as predictive associations rather than causal effects. Finally, we compared three machine-learning survival models and an ensemble using C-index and Brier score, selected the best-performing approach for feature-importance and simulation analyses, and evaluated eight movement scenarios over three simulated beekeeping seasons. Our model-comparison results highlight the importance of appropriate data structuring for achieving optimal performance with censored outcomes.
Language: English
Subfield: Insect Science
Open Access status: gold
Estimated APC paid: $2,690
OpenAlex ID: W7167800985
FWCI:
Cites: 24
Cited by:
Related to: 9