Letizia Lamperti

and 9 more

1. Metabarcoding of environmental DNA (eDNA) has recently improved our understanding of biodiversity patterns in marine and terrestrial ecosystems. However, the complexity of these data prevents current methods to extract and analyze all the relevant ecological information they contain. Therefore, ecological modeling could greatly benefit from new methods providing better dimensionality reduction and clustering. 2. Here we present two new deep learning-based methods that combine different types of neural networks to ordinate eDNA samples and visualize ecosystem properties in a two-dimensional space: the first is based on variational autoencoders (VAEs) and the second on deep metric learning (DML). The strength of our new methods lies in the combination of several inputs: the number of sequences found for each molecular operational taxonomic unit (MOTU), together with the genetic sequence information of each detected MOTU within an eDNA sample. 3. Using three different datasets, we show that our methods represent well three different ecological indicators in a two-dimensional latent space: MOTU richness per sample, sequence α-diversity per sample, and sequence ꞵ-diversity between samples. We show that our nonlinear methods are better at extracting features from eDNA datasets while avoiding the major biases associated with eDNA. Our methods outperform traditional dimension reduction methods such as Principal Component Analysis, t-distributed Stochastic Neighbour Embedding, and Uniform Manifold Approximation and Projection for dimension reduction. 4. Our results suggest that neural networks provide a more efficient way of extracting structure from eDNA metabarcoding data, thereby improving their ecological interpretation and thus biodiversity monitoring.

François Munoz

and 21 more

Although how rare species persist in communities is a major ecological question, the critical phenotypic dimension of rarity is broadly overlooked. Recent work has shown that evaluating functional distinctiveness, the average trait distance of a species to other species in a community, offers essential insights into biodiversity dynamics, ecosystem functioning, and biological conservation. However, the ecological mechanisms underlying the persistence of functionally distinct species are poorly understood. Here we propose a heterogeneous fitness landscape framework, whereby functional dimensions encompass peaks representing trait combinations that yield positive intrinsic growth rates in a community. We identify four fundamental causes leading to the persistence of functionally distinct species in a community. First, environmental heterogeneity or alternative phenotypic designs can drive positive population growth of functionally distinct species. Second, sink populations with negative growth can deviate from local fitness peaks and be functionally distinct. Third, species found at the margin of the fitness landscape can persist but be functionally distinct. Fourth, biotic interactions (either positive or negative) can dynamically alter the fitness landscape. We offer examples of these four cases and some guidelines to distinguish among them. In addition to these deterministic processes, we also explore how stochastic dispersal limitation can yield functional distinctiveness.