Between 1925 – 1929, approximately 12 non-native mountain goats (Oreamnos americanus) were translocated from Alaska and British Columbia to the foothills of the Olympic Range, USA. By 1970, descendants of these goats had colonized the entire Olympic Range and concerns about the management of this introduced species developed as damage to alpine soil and vegetation occurred. A series of removals reduced the population from 1,175 in 1983 to 389 goats by 1990, followed by a period a stasis and growth indicated again in 2011 and 2016. We used empirical demographic and genetic data to parameterize a population genetics individual-based simulation model of the Olympic Range mountain goat population. We calibrated the model to simulate the population trajectory for Olympic mountain goats from establishment in 1925 through the 1983 census, and validated model dynamics by simulating the period from 1990 to 2016. Modeled population dispersal closely tracked anecdotal reports. However, observed heterozygosity did not align with published research, suggesting a process not accounted for within the simulation model, such as a bottleneck, founder effect, or population trajectory dynamics. Sensitivity analyses showed that changes in annual reproductive rate had the greatest influence on population trajectories, followed by juvenile mortality and adult female mortality, respectively. The modeled population showed that approximately 80% of the total animals removed during the 1980’s needed to be female in order for the observed population stasis to occur. This model has the potential to be used more widely with established or introduced mountain goat populations in other regions.

We introduce a new R package ‘MrIML’ (Multi-response Interpretable Machine Learning). MrIML provides a powerful and interpretable framework that enables users to harness recent advances in machine learning to map multi-locus genomic relationships, to identify loci of interest for future landscape genetics studies and to gain new insights into adaptation across environmental gradients. Relationships between genetic change and environment are often non-linear, interactive and autocorrelated. Our package helps capture this complexity and offers functions that construct, fit and conduct inference on a wide range of highly flexible models that are routinely used for single-locus landscape genetics studies but are rarely extended to estimate response functions for multiple loci. To demonstrate the package’s broad functionality, we test its ability to recover landscape relationships from simulated genomic data. We also apply the package to two empirical case studies. In the first we estimate variation in the population-level genetic composition of North American balsam poplar (Populus balsamifera, Salicaceae) and in the second we recover individual-level landscapes while estimating host drivers of feline immunodeficiency virus genetic spread in bobcats (Lynx rufus). The ability to model thousands of loci collectively and compare models from linear regression to extreme gradient boosting, within the same analytical framework, has the potential to be transformative. The MrIML framework is also extendable and not limited to mapping genetic change, for example, it can be used to quantify the environmental driver sof microbiomes and coinfection dynamics.