Quantifying the impact of pesticides on learning and memory in bees

Abstract

Most insecticides are insect neurotoxins. Evidence is emerging that sublethal doses of these neurotoxins are affecting the learning and memory of both wild and managed bee colonies, exacerbating the negative effects of pesticide exposure and reducing individual foraging efficiency.Variation in methodologies and interpretation of results across studies has precluded the quantitative evaluation of these impacts that is needed to make recommendations for policy change. It is not clear whether robust effects occur under acute exposure regimes (often argued to be more field-realistic than the chronic regimes upon which many studies are based), for field-realistic dosages, and for pesticides other than neonicotinoids.Here we use meta-analysis to examine the impact of pesticides on bee performance in proboscis extension-based learning assays, the paradigm most commonly used to assess learning and memory in bees. We draw together 104 (learning) and 167 (memory) estimated effect sizes across a diverse range of studies.We detected significant negative effects of pesticides on learning and memory (i) at field realistic dosages, (ii) under both chronic and acute application, and (iii) for both neonicotinoid and non-neonicotinoid pesticides groups.We also expose key gaps in the literature that include a critical lack of studies on non-Apis bees, on larval exposure (potentially one of the major exposure routes), and on performance in alternative learning paradigms. Policy implications. Procedures for the registration of new pesticides within EU member states now typically require assessment of risks to pollinators if potential target crops are attractive to bees. However, our results provide robust quantitative evidence for subtle, sublethal effects, the consequences of which are unlikely to be detected within small-scale prelicensing laboratory or field trials, but can be critical when pesticides are used at a landscape scale. Our findings highlight the need for long-term postlicensing environmental safety monitoring as a requirement within licensing policy for plant protection products.

Keywords: agricultural policy; bees; cognition; insecticide; neonicotinoid; pesticide; pollination; pollinators.

Figure 1

Hedges’ d values ± 95% confidence intervals for effects of pesticides on (a) learning ability (b) memory

Figure 2

Mean effect size estimates (± 95% confidence intervals) for subsets of the data on the effects of pesticides on (a) learning and (b) memory. Number of studies (k) and number of effect sizes (n) are given for each subgroup [Colour figure can be viewed at wileyonlinelibrary.com]