Deep Multi-Species Embedding

TL;DR

This paper introduces Deep Multi-Species Embedding (DMSE), a neural network-based model that jointly embeds multiple species and environmental factors to better understand species distributions and interactions, outperforming traditional models.

Contribution

The paper presents a novel deep neural network approach for joint species embedding that captures inter-species relationships and shared habitat preferences, improving distribution predictions.

Findings

DMSE outperforms single-species models like random forests and SVMs.

The model uncovers meaningful inter-species relationships.

Graphical embeddings visualize bird species interactions in the Northeast US.

Abstract

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.