Deep Multi-Species Embedding
This work addresses the challenge of multi-species distribution modeling in biodiversity research, which is incremental as it builds on existing ecological evidence and methods.
The authors tackled the problem of modeling species distributions by proposing Deep Multi-Species Embedding (DMSE), a method that jointly embeds multiple species and environmental covariates using a deep neural network, and demonstrated that it outperforms single-species models and other multi-label models on bird data from eBird.
Understanding how species are distributed across landscapes over time is a fundamental question in biodiversity research. Unfortunately, most species distribution models only target a single species at a time, despite strong ecological evidence that species are not independently distributed. We propose Deep Multi-Species Embedding (DMSE), which jointly embeds vectors corresponding to multiple species as well as vectors representing environmental covariates into a common high-dimensional feature space via a deep neural network. Applied to bird observational data from the citizen science project \textit{eBird}, we demonstrate how the DMSE model discovers inter-species relationships to outperform single-species distribution models (random forests and SVMs) as well as competing multi-label models. Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling. An important domain contribution of the DMSE model is the ability to discover and describe species interactions while simultaneously learning the shared habitat preferences among species. As an additional contribution, we provide a graphical embedding of hundreds of bird species in the Northeast US.