Ilhem Bouderbala

Behavioural state inference from movement and environmental data using Markovian step selection functions

This paper introduces a framework using Hidden Markov Models with Step Selection Functions to infer behavioural states from movement and environmental data, showing improved accuracy in identifying ecologically meaningful states.

When indicator species identified from a network structure predict biodiversity

The paper evaluates using indicator species from co-occurrence networks to predict biodiversity, finding they can reconstruct species assemblages but are often outperformed by climate-based models.