Datasets, Analysis Scripts, and Supplementary Materials for Predicting Tree Species Diversity and Carbon Sequestration Using AI

Predicting Tree Species Diversity and Carbon Sequestration Using AI The repository contains: cleaned forest inventory datasets from ten forest reserves in southwestern Nigeria species abundance and biodiversity datasets Random Forest, XGBoost, and Linear Regression modelling scripts Generalized Linear Latent Variable Model (GLLVM) analyses cross-validation workflows supplementary tables and diagnostics interactive dashboard source code documentation describing the analytical workflow The study combines primary field measurements from Emerald Forest Reserve with archived forest inventory datasets from nine additional forest reserves to investigate relationships between forest structure, biodiversity, biomass, carbon stock, and machine learning model performance. This repository has been archived to support transparency, reproducibility, and long-term accessibility of the research.