Dispersal inference from population genetic variation using a convolutional neural network

The geographic nature of biological dispersal shapes patterns of genetic variation over landscapes, so that it is possible to infer properties of dispersal from genetic variation data. Here we present an inference tool that uses geographically-referenced genotype data in combination with a convolutional neural network to estimate a critical population parameter: the mean per-generation dispersal distance. Using extensive simulation, we show that our deep learning approach is competitive with or outperforms state-of-the-art methods, particularly at small sample sizes (e.g., n = 10). In addition, we evaluate varying nuisance parameters during training—including population density, population size changes, habitat size, and the size of the sampling window relative to the full habitat—and show that this strategy is effective for estimating dispersal distance when other model parameters are unknown. Whereas competing methods depend on information about local population density or accurate identification of identity-by-descent tracts as input, our method uses only single-nucleotide-polymorphism data and the spatial scale of sampling as input. These features make our method, which we call disperseNN, a potentially valuable new tool for estimating dispersal distance in non-model systems with whole genome data or reduced representation data. We apply disperseNN to 12 different species with publicly available data, yielding reasonable estimates for most species. Importantly, our method estimated consistently larger dispersal distances than mark-recapture calculations in the same species, which may be due to the limited geographic sampling area covered by some mark-recapture studies. Thus genetic tools like ours complement direct methods for improving our understanding of dispersal. ### Competing Interest Statement The authors have declared no competing interest.