A Reproducible Simulation Framework for Benchmarking Artificial Intelligence Models in Automated Biodiversity Monitoring Under Imperfect Detection - Supplementary Code S1
This repository contains the complete, annotated R script (Supplementary Code S1) accompanying the manuscript "A Reproducible Simulation Framework for Benchmarking Artificial Intelligence Models in Automated Biodiversity Monitoring Under Imperfect Detection" submitted to Scientific Reports (Special Issue: Automated Biodiversity Monitoring). The script implements a fully reproducible virtual ecologist simulation framework that benchmarks three modelling approaches - Generalized Linear Models (GLM), Random Forest, and Extreme Gradient Boosting (XGBoost) - for species richness estimation under imperfect and heterogeneous detection probability. S
Resource information
- Format
- r
- Original repository
- 20021056
- DOI
- 10.5281/zenodo.20021056
- Credit basis
- Creators in Zenodo record metadata
- Access
- Open files available from the original Zenodo deposit
- Last checked
- Nov 5, 2026
- License
- Not specified
- Last record update
- Nov 5, 2026
About this resource
This repository contains the complete, annotated R script (Supplementary Code S1) accompanying the manuscript "A Reproducible Simulation Framework for Benchmarking Artificial Intelligence Models in Automated Biodiversity Monitoring Under Imperfect Detection" submitted to Scientific Reports (Special Issue: Automated Biodiversity Monitoring). The script implements a fully reproducible virtual ecologist simulation framework that benchmarks three modelling approaches - Generalized Linear Models (GLM), Random Forest, and Extreme Gradient Boosting (XGBoost) - for species richness estimation under imperfect and heterogeneous detection probability. Six integrated analyses are included: multi metric model comparison, one-way ANOVA with Tukey HSD post-hoc tests, 5-fold cross-validation, bootstrap 95% confidence intervals, Random Forest variable importance and partial dependence analysis, detection probability sensitivity analysis, and a novel 5×5 factorial analysis crossing detection probability against sample size. Seven high quality figures are exported at 300 dpi. R version 4.4.2 was used. All results are fully reproducible using set.seed(123).