Trends in soil organic carbon prediction research using geospatial technologies and artificial intelligence: an exploratory bibliometric analysis (2005-2025)
- 1Laboratory of Geosciences and Natural Resources, Ibn Tofail University, Faculty of Sciences, Kenitra, Morocco; Corresponding author.
- 2Department of Soil and Water Biodiversity, National Forestry School of Engineers, Sale, Morocco
- 3Laboratory of Geosciences and Natural Resources, Ibn Tofail University, Faculty of Sciences, Kenitra, Morocco
Abstract
Soil organic carbon (SOC) is central to soil fertility and climate regulation, and its spatial prediction increasingly relies on geospatial technologies and artificial intelligence (AI). Existing bibliometric studies and reviews have examined remote sensing-based soil organic matter monitoring, agricultural SOC components, or digital soil mapping separately, a bibliometric synthesis of how these strands have converged into GeoAI (geospatial AI: the integration of AI with spatially explicit data) for SOC prediction is lacking. This study presents an exploratory bibliometric analysis of SOC prediction research from 2005 to 2025. Scopus was searched on 25 March 2026 with a field-tagged Boolean query restricted to English-language journal articles, after screening and duplicate removal, 1561 articles were analyzed with Bibliometrix in R (performance analysis, co-authorship, co-citation, keyword co-occurrence). The annual growth rate was 28.68%, output rose sharply after 2018 and exceeded 300 articles in 2024, 40.49% of articles involved international co-authorship, and documents averaged 43.67 citations. China and the United States led in total citations (16,602 and 8,006, respectively), and China led in output. Geoderma, Science of the Total Environment, and Environmental Monitoring and Assessment were the most frequent sources, keyword analysis identified machine learning, remote sensing, and digital soil mapping as the methodological core. Output, citations and collaboration were concentrated in a few countries, with Africa, South Asia, and parts of Latin America underrepresented, which may limit model transferability, causes were not measured. As the analysis is bibliometric, findings describe research trends, not model performance or environmental outcomes.
Related
- Integrating machine learning and geospatial technologies for spatio-temporal analysis of urban expansion and land use transformation in Gambella Town, Ethiopia
- An Artificial Intelligence Integrated Geospatial Decision-Support Framework for Scenario-Based Climate-Adaptive Land-Use Optimization and Environmental Risk Reduction
- From Equations to Geospatial Foundation models. What comes next for forest prediction?
- Artificial intelligence-enabled monitoring of pesticide contamination in agricultural water systems: a comprehensive review of intelligent sensing technologies for water quality surveillance and environmental risk assessment
- A geospatial and community perception analysis of the impacts of land use and land cover change on ecosystem service values
BibTeX
@article{khaddi2026trends,
title = {{Trends in soil organic carbon prediction research using geospatial technologies and artificial intelligence: an exploratory bibliometric analysis (2005-2025)}},
author = {Elhoussaine Khaddi and Hafida Zaher and Hafida Naim},
journal = {Environmental and Sustainability Indicators},
year = {2026},
month = oct,
doi = {10.1016/j.indic.2026.101585},
url = {https://doi.org/10.1016/j.indic.2026.101585},
note = {CC BY},
}
RIS
TY - JOUR
TI - Trends in soil organic carbon prediction research using geospatial technologies and artificial intelligence: an exploratory bibliometric analysis (2005-2025)
AU - Elhoussaine Khaddi
AU - Hafida Zaher
AU - Hafida Naim
PY - 2026
DA - 2026/10/30
JO - Environmental and Sustainability Indicators
DO - 10.1016/j.indic.2026.101585
UR - https://doi.org/10.1016/j.indic.2026.101585
AB - Soil organic carbon (SOC) is central to soil fertility and climate regulation, and its spatial prediction increasingly relies on geospatial technologies and artificial intelligence (AI). Existing bibliometric studies and reviews have examined remote sensing-based soil organic matter monitoring, agricultural SOC components, or digital soil mapping separately, a bibliometric synthesis of how these strands have converged into GeoAI (geospatial AI: the integration of AI with spatially explicit data) for SOC prediction is lacking. This study presents an exploratory bibliometric analysis of SOC prediction research from 2005 to 2025. Scopus was searched on 25 March 2026 with a field-tagged Boolean query restricted to English-language journal articles, after screening and duplicate removal, 1561 articles were analyzed with Bibliometrix in R (performance analysis, co-authorship, co-citation, keyword co-occurrence). The annual growth rate was 28.68%, output rose sharply after 2018 and exceeded 300 articles in 2024, 40.49% of articles involved international co-authorship, and documents averaged 43.67 citations. China and the United States led in total citations (16,602 and 8,006, respectively), and China led in output. Geoderma, Science of the Total Environment, and Environmental Monitoring and Assessment were the most frequent sources, keyword analysis identified machine learning, remote sensing, and digital soil mapping as the methodological core. Output, citations and collaboration were concentrated in a few countries, with Africa, South Asia, and parts of Latin America underrepresented, which may limit model transferability, causes were not measured. As the analysis is bibliometric, findings describe research trends, not model performance or environmental outcomes.
SN - 2665-9727
ER -