Finding ecologically relevant relationships between environmental covariates and response variables requires determining appropriate scales of effect. While considering multiple spatial scales of effect in hierarchical models has been the focus of recent studies, the effect of spatiotemporal scales, and temporal resolution of data on habitat suitability and species abundance has received less attention. We investigated relationships between ringnecked pheasant rooster abundance and environmental covariates with the goal of identifying important variables and their scales of effect in South Dakota, U.S.A. Using a suite of remote sensing data, we examined whether seasonal environmental conditions influence pheasant relative abundance and how survey conditions might affect detectability of roosters. To select optimal scales of effect and the best subset of covariates simultaneously, we employed a Reversible-Jump Monte Carlo Markov Chain (RJMCMC) approach in a Bayesian framework. We explored sources of uncertainty in data and controlled them through consideration of random effects. The use of seasonal covariates in addition to annual covariates revealed differential effects on species abundance. The proportion of grasslands on the landscape was an important covariate in models in all years, with rooster abundance generally being highest at intermediate levels of grassland density at local scales of effect. Pheasant abundance was also positively related to the proportion of small grain crop cover on the landscape at >2 km scales. Spring gross primary productivity and percentage of herbaceous wetlands on the landscape, both at a large scale (8 km), were the most important covariates in the wet years of 2018 and 2019 and were positively related to pheasant abundance. Grasslands at intermediate levels of density explained variability of pheasant abundance. However, other variables important to pheasant relative abundance varied among years depending on prevailing weather and climate conditions. Our workflow to model relationships between relative abundance and habitat components for pheasants can also be employed to model count data for other species to inform management decisions.
