Predicting and prioritizing species coexistence: learning outcomes via experiments

Abstract

AbstractPredicting species coexistence can be difficult often because underlying assembly processes are unknown and data are limited. However, accurate predictions are needed for design and forecasting problems in biodiversity conservation, climate change, invasion ecology, restoration ecology, and synthetic ecology. Here we describe an approach (Learning Outcomes Via Experiments; LOVE) where a limited set of experiments are conducted and multiple community outcomes measured (richness, composition, and abundance), from which a model is trained to predict outcomes for arbitrary experiments. Across seven taxonomically datasets, LOVE predicts test outcomes with low error when trained on ∼100 randomly-selected experiments. LOVE can then prioritize experiments for tasks like maximizing outcome richness or total abundance, or minimizing abundances of unwanted species. LOVE complements existing mechanism-first approaches to prediction and shows that rapid screening of communities for desirable properties may become possible.Author summaryPredicting which species will or will not coexist with each other is a central challenge for ecology. Success would allow experimental assembly of communities with desirable properties (e.g. high biodiversity). Mechanistic approaches to this problem run into data and theory limitations, as well as vast combinatorial complexity. Here we instead show to predict and prioritize coexistence without needing to identify or quantify any ecological mechanisms, based on statistical learning from randomly-selected experiments. The approach may help us to discover and then assemble ecological communities with desirable properties.