Food web reconstruction through phylogenetic transfer of low‐rank network representation

Abstract

transfer learning ancestral character estimation biogeography 1. Despite their importance in many ecological processes, collecting data and information on ecological interactions is an exceedingly challenging task. For this reason, large parts of the world have a data deficit when it comes to species interactions, and how the resulting networks are structured. As data collection alone is unlikely to be sufficient, community ecologists must adopt predictive methods.2. We present a methodological framework that uses graph embedding and transfer learning to assemble a predicted list of trophic interactions of a species pool for which their interactions are unknown. Specifically, we 'learn' the information (latent traits) of species from a known interaction network and infer the latent traits of another species pool for which we have no a priori interaction data based on their phylogenetic relatedness to species from the known network. The latent traits can then be used to predict interactions and construct an interaction network.3. Here we assembled a metaweb for Canadian mammals derived from interactions in the European food web, despite only 4% of common species being shared between the two locations. The results of the predictive model are compared against databases of recorded pairwise interactions, showing that we correctly recover 91% of known interactions.4. The framework itself is robust even when the known network is incomplete or contains spurious interactions making it an ideal candidate as a tool for filling gaps when it comes to species interactions. We provide guidance on how this framework can be adapted by substituting some approaches or predictors in order to make it more generally applicable.

Addressing the Eltonian shortfall with trait‐based interaction models

“…Because how species choose their prey tends to be evolutionary conserved, phylogenetic relationships could inform how regression coefficients correlate across clades (Gómez et al, 2010). Second, phylogenetic relationships can directly make predictions given enough interaction data (Elmasri et al, 2020), or to transfer species interaction knowledge between systems (Strydom, Bouskila, et al, 2021). Third, machine learning algorithms have been used to predict interactions within networks (i.e.…”

Minimizing Data Waste: Conservation in the Big Data Era

“…In addition, this presentation showed how open data could help extend uniqueness assessments to species interactions. They combined community predictions with an open interaction metaweb (Strydom et al 2022) to produce localized predictions of ecological networks, then measured uniqueness separately based on interaction and community composition (Poisot et al 2017). Interaction uniqueness showed a different spatial distribution from community uniqueness over whole regions, highlighting that sites and areas may be unique in one community aspect and not the other (e.g.…”

Predicting predator-prey interactions in terrestrial endotherms using random forest

“…Importantly, such 'false non-interactions' in training data likely reduce the reliability of interactions and non-interactions inferred from random forests and other classifiers. Similarly, random forests and other classifiers trained on datasets that are taxonomically biased might perform poorly when making predictions for species not represented in the training data (Strydom et al 2022).…”