A Scientometric and Taxonomic Review of Global Habitat Suitability Research (1947–2024)

Habitat suitability (HS) studies play a crucial role in sustainable development practices. In recent years, the global community has aimed to mitigate the loss of biodiversity due to climate change and focuses on sustainability. There have been growing studies in HS and it is necessary to map this research domain for broader understanding and future research direction. In this study, we explored the 38,746 HS related documents indexed in the Scopus database between 1947 and 2024 applying bibliometric technique coupled with the Latent Dirichlet Allocation (LDA) unsupervised machine learning model. The scientific names of species were mined from the abstract of the articles using binomial nomenclature pattern phrases search technique and mapped to the Global Biodiversity Information Facility (GBIF) taxonomy database. As a result, we observed an increasing trend of statistically reliable publications followed the Benford law (P-value > 0.308). The United States of America authored the highest number of publications followed by the People's Republic of China and the United Kingdom. From the LDA model, six thematic topics: ecological modeling, habitat suitability, bioactivity and integrity, species interactions, habitat quality, and taxonomy environmental modeling were observed. While mapping the scientific names of the extracted species to the GBIF database, we observed the HS research was mainly centered on the Animalia kingdom followed by plants, fungi, and chromista. In habitat suitability studies, species such as Salmo trutta (Animalia), Phragmites australis (Plantae), Escherichia coli (Bacteria), Plasmodium falciparum (Chromista), Trypanosoma cruzi (Protista), and Batrachochytrium dendrobatidis (Fungi) were identified as dominant representatives within their respective biological domains. This study reveals a comprehensive analysis of trends, latent thematic structures, suitability modeling approaches, and cross-kingdom analysis of species used in HS research, revealing ecological biases. The approach and findings of this research offer insights for researchers, conservationists, and policymakers for data-driven environmental management and sustainable conservation practices.