Consensus methods based on machine learning techniques for marine phytoplankton presence-absence prediction

Mathias Bourel, Carolina Crisci, Ana Martínez

Abstract: Highlights•We present six non-homogeneous consensus models to predict the presence–absence of marine phytoplankton species.•In most of the cases, the consensus models behaved better than the single-models that were used to construct them.•The single-models considered were generalized linear models, random forests, boosting and support vector machines.•Our results suggest that attention must be given to consensus methods when dealing with ecological prediction.