Artificial Intelligence (AI)‐Driven Precision Liming in Optimized Soil pH to Ensure Global Food Security and Sustainable Agriculture: A Systematic Review
The Scientific World Journal · 2026-01 · 2026 (1)
DOI: 10.1155/tswj/2566808 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift The Scientific World Journal, online erschienen am 21.11.2026. Verfasst von Simeneh Gedefaw Abate und 1 weiteren Autor:innen. Die Arbeit nennt 116 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Soil pH is a critical determinant of agricultural productivity, influencing nutrient availability, microbial activity, and plant growth, with an optimal range of 6.0–6.8 widely recognized for most field crops. Acidic soil worldwide accounts for approximately 40% to 50% of potential arable land. Traditional liming (using calcium‐rich and magnesium‐rich materials) corrects soil acidity caused by natural and anthropogenic factors but often overlooks the spatial variability of soil pH, leading to inefficient resource use and environmental harm. Moreover, precision liming studies have limited ability to optimize soil pH, unlike machine learning (ML)‐driven and artificial intelligence (AI)‐driven land use and land cover studies. Therefore, precision liming, enabled by variable rate application (VRA), offers a targeted solution to optimize soil pH, enhance yields, and reduce costs and ecological impacts. Recent advancements in AI and ML are transforming precision agriculture by integrating data from remote sensing, soil sensors, and historical records to generate detailed soil pH maps and predictive models. This systematic review synthesizes literature sourced from Google Scholar, ScienceDirect, Springer Nature, and IEEE to explore AI and ML applications in precision liming. Findings indicated that the majority of AI‐based soil pH prediction models exhibited excellent prediction ability, achieving a classification accuracy ranging from 85.41% to 97%, a determination coefficient ( R 2 ) of 0.60–0.96, and an RMSE of as low as 0.08 pH units, indicating their significant potential in aiding accurate site‐specific precision liming and sustainable soil management. However, challenges such as data quality, computational demands, and adoption barriers persist. In addition, the ranges of these prediction performance metrics findings are not from the common benchmarks rather they are from heterogenous studies. This review identifies research gaps, particularly the scarcity of direct studies on AI‐driven liming, and proposes future directions, including robust model development, multisource data integration, and economic analyses. By leveraging AI, precision liming can advance sustainable agriculture, supporting global food security for a projected population of 9.7 billion by 2050.
Zitieren
APA
Abate, S. G., & Liu, F. (2026). Artificial Intelligence (AI)‐Driven Precision Liming in Optimized Soil pH to Ensure Global Food Security and Sustainable Agriculture: A Systematic Review. The Scientific World Journal, 2026(1). https://doi.org/10.1155/tswj/2566808
Vancouver
Abate SG, Liu F. Artificial Intelligence (AI)‐Driven Precision Liming in Optimized Soil pH to Ensure Global Food Security and Sustainable Agriculture: A Systematic Review. The Scientific World Journal. 2026;2026(1). doi:10.1155/tswj/2566808
BibTeX
@article{Abate2026,
author = {Abate, Simeneh Gedefaw and Liu, Feng},
title = {Artificial Intelligence (AI)‐Driven Precision Liming in Optimized Soil pH to Ensure Global Food Security and Sustainable Agriculture: A Systematic Review},
journal = {The Scientific World Journal},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1155/tswj/2566808}
}
EUVIMED