Dataset and Results for: A Data-Driven Analysis of Forest Carbon Remote Sensing: From Vegetation Indices to Artificial Intelligence

This repository contains the dataset and analysis results associated with the article: "A Data-Driven Analysis of Forest Carbon Remote Sensing: From Vegetation Indices to Artificial Intelligence" The dataset includes a large-scale bibliometric corpus of 29,773 publications retrieved from the Web of Science and Scopus databases, covering the period 2021–2025. The results encompass bibliometric performance analyses, network analyses conducted using Biblioshiny (Bibliometrix R package), and Latent Dirichlet Allocation (LDA) topic modeling outputs (k=20) generated via the Gensim Python library. Data merging, deduplication, and preparation were performed using BibexPy software.