Toxicological assessment of agrochemicals on bees using machine learning tools

Abstract

Machine learning (ML) is a branch of artificial intelligence (AI) that enables the analysis of complex multivariate data. ML has significant potential in risk assessments of non-target insects for modeling the multiple factors affecting insect health, including the adverse effects of agrochemicals. Here, the potential of ML for risk assessments of glyphosate (herbicide; formulation) and imidacloprid (insecticide, neonicotinoid; formulation) on the stingless bee Melipona quadrifasciata was explored. The collective behavior of forager bees was analyzed after in vitro exposure to agrochemicals. ML algorithms were applied to identify the agrochemicals that the bees have been exposed to based on multivariate behavioral features. Changes in the in situ detection of different proteins in the midgut were also studied. Imidacloprid exposure leads to the greatest changes in behavior. The ML algorithms achieved a higher accuracy (up to 91%) in identifying agrochemical contamination. The two agrochemicals altered the detection of cells positive for different proteins, which can be detrimental to midgut physiology. This study provides a holistic assessment of the sublethal effects of glyphosate and imidacloprid on a key pollinator. The procedures used here can be applied in future studies to monitor and predict multiple environmental factors affecting insect health in the field.

Keywords: Artificial intelligence; Ecotoxicology; Physiological response; Pollinators; Risk assessment.