Predicting species composition when environmental drivers are missing

2014-01-12T02:25:35Z (GMT) by David Harris
<p>Species distribution models provide valuable tools for marking species’ range limits and predicting individual species’ responses to environmental change.</p> <p>However, multi-species patterns like richness and co-occurrence involve correlations among species, and the processes driving these correlations are not always observable.</p> <p>In other words, some sites will be less suitable or more suitable for a group of species than expected by these models, depending on variables that have not even been measured.</p> <p>Current (nonlinear) models cannot account for these variables, which limits their utility for community ecology.</p> <p>How can we predict species composition without knowing what these unmeasured factors are or how they affect community assembly?</p> <p>I designed a stochastic neural network[4] (to be made available as an R package called mistnet). The model uses latent random variables (Z) for unobserved environmental factors. Since these variables can take on a range of values, the model can make a range of distinct predictions for a given set of environmental data.</p>