Marie‐Pierre Étienne

This paper introduces a method to incorporate classification uncertainty from machine learning into ecological models using Monte Carlo simulations, showing it leads to more reliable ecological estimates.

The paper compares discrete- and continuous-time models for detecting covariates in occupancy and N-mixture models, showing that temporal resolution affects detection estimates but not abundance or occupancy.

The paper develops a Hierarchical Bayesian Model to estimate predation rates using molecular detection data and field/laboratory observations, applied to carabid beetles in agricultural fields.

The paper develops a Bayesian occupancy model that incorporates informative priors to address identifiability issues caused by identification errors in passive bio-monitoring data.

This study compares discrete- and continuous-time occupancy models for analyzing continuously collected biodiversity data, finding that simpler models often suffice for occupancy estimation.