Modeling Joint Abundance of Multiple Species Using Dirichlet Process Random Effects

We present a method for modeling multiple species distributions simultaneously using Dirich1 let Process random effects to cluster species into guilds. Guilds are ecological groups of 2 species that behave or react similarly to some environmental conditions. By modeling latent 3 guild structure, we capture the cross-correlations in abundance or occurrence of species over 4 surveys. In addition, ecological information about the community structure is obtained as 5 a byproduct of the model. By clustering species into similar functional groups, prediction 6 uncertainty of community structure at additional sites is reduced over treating each species 7 separately. The method is illustrated with a small simulation demonstration, as well as an 8 analysis of a mesopelagic fish survey from the eastern Bering Sea near Alaska. The simula9 tion data analysis shows that guild membership can be extracted as the differences between 10 groups become larger and if guild differences are small the model naturally collapses all the 11 species into a small number of guilds which increases predictive efficiency by reducing the 12 number of parameters to that which is supported by the data. 13