Machine Learning and Artificial Intelligence Applications in Soil Science
Budiman Minasny, Alex B. McBratney
Abstract
ABSTRACT The awarding of the Nobel Prize in Physics to pioneers in neural networks highlights their substantial influence across diverse disciplines, including soil science. This article explores the evolution and transformative impact of machine learning and artificial intelligence (AI) in soil science. These technologies have revolutionised the modelling of complex soil processes, enhancing our ability to predict and map soil properties, simulate water movement and assess global soil carbon dynamics. The article discusses future directions for AI in soil science, such as developing new mathematical soil matrices and integrating AI with soil science knowledge to improve the precision and efficiency of soil assessments. As AI evolves, its potential in soil science includes generating new hypotheses, optimising soil carbon–mineral associations for better sequestration and enhancing soil phenotyping with high‐throughput data analysis. Integrating AI with physical models could lead to more precise, data‐driven soil management practices that support net‐zero, nature‐positive stewardship for improved soil security.