Faecal metabarcoding reveals pervasive long-distance impacts of garden bird feeding

Abstract

Supplementary feeding of wildlife is widespread, being undertaken by more than half of households in many countries. However, the impact that these supplemental resources have is unclear, with impacts largely considered to be restricted to urban ecosystems. We reveal the pervasiveness of supplementary foodstuffs in the diet of a wild bird using metabarcoding of blue tit (Cyanistes caeruleus) faeces collected in early spring from a 220 km transect in Scotland with a large urbanization gradient. Supplementary foodstuffs were present in the majority of samples, with peanut (Arachis hypogaea) the single commonest (either natural or supplementary) dietary item. Consumption rates exhibited a distance decay from human habitation but remained high at several hundred metres from the nearest household and continued to our study limit of 1.4 km distant. Supplementary food consumption was associated with a near quadrupling of blue tit breeding density and a 5-day advancement of breeding phenology. We show that woodland bird species using supplementary food have increasing UK population trends, while species that do not, and/or are outcompeted by blue tits, are likely to be declining. We suggest that the impacts of supplementary feeding are larger and more spatially extensive than currently appreciated and could be disrupting population and ecosystem dynamics.

Keywords: breeding density; diet; human–wildlife interaction; phenology; population change; supplementary provisioning.

Figure 1.

Effects of (a) distance to nearest human habitation and (b) sampling date (adjusted for the phenology of the site within year) on the probability of supplementary food consumption by blue tits. The predicted response of each is shown in 2014 (gold) and 2015 (green). Asterisks in (a) show the proportion of faeces containing supplementary foodstuff per site per year (2014 gold, 2015 green), not the per sample presence/absence response analysed in the model. (Online version in colour.)

Figure 2.

Effects of site-level supplementary food intake on (a) probability of nest-box occupancy and (b) first egg laying date. Asterisks in (a) depict site per year occupancy rates rather than the 0/1 occupied response per nest-box analysed in the model. Predictions correspond to 2014. (Online version in colour.)

Figure 3.

Differing population trends of 20 insectivorous woodland bird species in the UK with regard to (i) supplementary garden feeder usage, (ii) behavioural dominance in comparison to blue tits and (iii) whether the species competes for nest sites with blue tits, with values depicting mean ± standard error with an asterisk above a significant difference as determined by a t-test. A trend value of 1 represents a large population decline (>−50%) and 5 a large population increase (greater than 50%) over 25 years, with a stable population (trend value = 3) shown by a grey dashed line. (Online version in colour.)