1. Climate warming is predicted to have large effects on insects, yet several data shortfalls, including distributional information, impede effective conservation strategies. 2. Knowledge of species distributions is a critical component for assessing conservation need but is often lacking for endemic or rare taxa, especially invertebrates. 3. One approach to better inform this gap is by using species distribution modelling (SDM) to predict suitable habitat and guide field surveys. 4. Here, we combine the predictions of two machine learning algorithms, maximum entropy and Random Forest, to estimate the current and future distributions of two endemic dragonflies of the Ozark-Ouachita Interior Highlands region in the southcentral United States. 5. Current suitable areas predicted by both algorithms largely overlapped for each species, but different environmental variables were most important for predicting their distributions. Field validation of these models resulted in new detections for both species showing their utility in guiding subsequent field surveys. 6. Future projections under two climate change scenarios support maintaining current suitable areas as these are predicted to be strongholds for these species. Our results suggest that combining outputs of multiple species distribution models is a useful tool for better informing the distributions of geographically limited or rare species.

Numerous mechanisms can promote competitor coexistence. Yet, these mechanisms are often considered in isolation from one another. Consequently, whether multiple mechanisms shaping coexistence combine to promote or constrain species coexistence remains an open question. Here, we aim to understand how multiple mechanisms interact within and between life stages to determine frequency‐dependent population growth, which has a key role stabilizing local competitor coexistence. We conducted field experiments in three lakes manipulating relative frequencies of two Enallagma damselfly species to evaluate demographic contributions of three mechanisms affecting different fitness components across the life cycle: the effect of resource competition on individual growth rate, predation shaping mortality rates, and mating harassment determining fecundity. We then used a demographic model that incorporates carry‐over effects between life stages to decompose the relative effect of each fitness component generating frequency‐dependent population growth. This decomposition showed that fitness components combined to increase population growth rates for one species when rare, but they combined to decrease population growth rates for the other species when rare, leading to predicted exclusion in most lakes. Because interactions between fitness components within and between life stages vary among populations, these results show that local coexistence is population specific. Moreover, we show that multiple mechanisms do not necessarily increase competitor coexistence, as they can also combine to yield exclusion. Identifying coexistence mechanisms in other systems will require greater focus on determining contributions of different fitness components across the life cycle shaping competitor coexistence in a way that captures the potential for population‐level variation.

No abstract