Virginie Boreux

TL;DR: It is shown that not all pollinators are equally effective at pollinating apples, with hoverflies being less effective than solitary bees and bumblebees, and the relative abundance of different pollinator guilds visiting apple flowers of different varieties varies significantly.

TL;DR: This work identified ten important bee species for global pollination of crops and summarized bee-dependent ecosystem services to show how bees substantially contribute to food security, medical resources, soil formation or spiritual practices, highlighting their wide range of benefits for human well-being and to identify future research needs.

TL;DR: The authors compared conventional generalized linear models (GLM) with more flexible Machine Learning (ML) models (Random Forest, Boosted Regression Trees, Deep Neural Networks, CNN, Convolutional Neural Network, Support Vector Machines, Naïve Bayes, and kNN) for predicting species interactions in plant-hummingbird networks.

TL;DR: The results indicate that organic management is more efficient than integrated pest management in developing environmentally friendly apple orchards with higher species richness, and demonstrate that there is no inherent trade‐off between species richness and yield.

TL;DR: It is found that the best ML models can successfully predict species interactions in plant–pollinator networks, outperforming GLM models by a substantial margin, and that flexible ML models offer many advantages over traditional regression models for understanding interaction networks.