Grasslands have undergone extensive transformation globally from agricultural intensification and residential development, resulting in drastically reduced habitat area available to native butterfly populations. However, even fragmented semi-natural grasslands within an agricultural matrix can often support butterflies, as long as disturbance is frequent enough. Although disturbances like fire can affect butterflies negatively via direct mortality, butterfly populations often benefit subsequently, presumably through indirect effects on habitat quality. Managers have therefore embraced prescribed fires as a means to benefit rare or threatened grassland butterfly populations, yet the specific mechanisms underlying the indirect benefits of burning are poorly understood. In particular, the effect of prescribed fire on the distribution and population dynamics of butterfly host plants remains little studied. In this twelve-year study, we investigated the effect of prescribed fire on the host plants (Viola spp.) of an extremely rare butterfly, the eastern regal fritillary (Speyeria idalia idalia) on a military training area (Fort Indiantown Gap National Guard Training Center in southeastern Pennsylvania, USA). We fit plant monitoring and fire history data with hurdle (zero-altered negative binomial) models to determine to what extent fire is driving (1) the broad spatial and temporal distribution of violets, and (2) the local abundance of violets.
Results/Conclusions
Our results demonstrated a significant negative effect of time since fire on both presence and abundance of violets. Hurdle models revealed significant variation by site and year on the distribution and abundance of violets. Specifically, one site (D3) supported lower violet abundance than all other sites, while the probability of violet presence within sampling plots was higher at two other sites (B12 and R23). In addition, violets became abundant in recently burned areas and gradually declined with increasing time since fire. Further, violets became more aggregated over time – in 2015 they were present at fewer plots than earlier sampling years, but were at significantly higher abundances in plots where they were present. Our results indicate that prescribed fire management should be organized at the site level considering them as distinct management units. Our results further suggest that the sites supporting the remnant eastern regal fritillary population require periodic disturbance with prescribed fire to maintain their specialized host plants. Finally, these results clarify mechanisms underlying the positive indirect effects of fire on butterfly populations.