Machine learning of honey bee olfactory behavior identifies repellent odorants in free-flying bees in the field.

Machine learning identified over 130 repellent odorants for honey bees, with seven confirmed to strongly repel foraging bees in field tests.

• Why it matters: Protecting beneficial insects like honey bees from pesticides is critical for pollination and ecosystem health, but discovering effective repellents is hampered by complex olfactory systems and limited data.
• What they did: A machine-learning model was developed using honey bee olfactory behavior data to predict aversive chemical structures, refined with additional species-level behavioral testing, and screened over 50 million compounds.
• The result: The approach successfully identified and validated potent repellents, enabling targeted strategies to prevent pesticide contact and support pollinator conservation efforts.