European Dryland Biodiversity Projection Model: Code and Simulation Data (v1.0.0)

This repository contains the complete simulation code and datasets supporting the manuscript "Weighted Ensemble of Artificial Intelligence and Mechanistic Models for Extinction Risk Assessment in European Dryland Biodiversity". The package includes an AI-enhanced mechanistic ensemble biodiversity modeling framework that integrates ecological niche theory (40% weighting) with machine learning algorithms (Random Forest 30%, Gradient Boosting 30%) to project species distributions across 50 European dryland specialist species under four climate change scenarios (RCP2.6, RCP4.5, RCP6.0, and RCP8.5) from 1995 to 2024. Contents:- biodiversity_model.py: Complete Python implementation of the ensemble modeling framework- Six simulation output datasets (CSV format, ~2 MB total): • Species characteristics and trait data (n=50 species) • Study site geographic and environmental data (n=100 locations) • Climate projections for four RCP scenarios (1995-2024) • Biodiversity predictions including habitat suitability, occurrence probability, and extinction risk • Model validation metrics (TSS, AUC-ROC, sensitivity, specificity) • Conservation priority hotspots with species richness and protection status- Documentation (README, requirements.txt, LICENSE) The modeling framework integrates thermal performance functions, precipitation requirements, habitat fragmentation effects, and dispersal barriers with machine learning algorithms to generate evidence-based conservation guidance. Model validation employed five-block spatial cross-validation achieving mean TSS > 0.80 and AUC-ROC > 0.90. This code and data are fully reproducible. Running the Python script generates new simulation outputs with current timestamps. Computational requirements: Python 3.8+, 8GB RAM, approximately 25 minutes runtime for full simulation. For citation and usage instructions, see README.md. All code is released under MIT License.