As the world grapples with climate change and food security, soil science emerges as a pivotal player in adapting to these challenges. A recent paper published in Frontiers in Science explores the role of AI tools in enhancing our understanding of soils to mitigate climate impacts.
Soil systems, which are crucial for carbon storage and ecosystem support, are influenced by a variety of factors, including climate and agricultural practices. These systems are complex and not easily predictable, particularly under increasing climate and land-use pressures. Hence, innovative tools are essential for simplifying this complexity for researchers.
Currently, digital soil mapping and spectroscopy are some of the machine learning techniques employed in soil science. With the integration of AI, these approaches could be further advanced by developing digital soil twins, improving monitoring of soil microbiomes, and trialing climate adaptation strategies within simulated models for expedited results.
The paper emphasizes that AI has the capacity to revolutionize soil science by expediting initial phases of research, enhancing predictive capabilities for land-use and climate adaptation decisions, and managing intricate data, thereby allowing scientists to focus on more complex issues that require expert judgment.
According to Prof Alex McBratney from The University of Sydney, AI, when used in collaboration with experts, can significantly enhance our understanding of soil ecosystems. “In partnership with experts, AI could help us better match the complexity and ever-changing nature of soil ecosystems. Unlike current machine learning tools that focus on isolated tasks, these systems can mimic scientific collaboration to a highly sophisticated degree—combining reasoning, planning, and interdisciplinary insight to support researchers and drive significant progress.”
“Perception of the vital importance of soil in planetary functioning is increasing, and soil science will continue to grow and flourish under scientist-led AI,” he added.
Unveiling Soil’s Secrets
The research team demonstrated an innovative AI system tasked with examining scientific literature and developing theories on carbon storage in soils. The AI agents successfully proposed five hypotheses, including factors such as climate influence and management strategies, which were then evaluated through expert review processes, emulating elements of the scientific method with outputs aligning closely with established research.
Lead author Prof Budiman Minasny, also from The University of Sydney, highlighted the potential of AI in soil research. “Our findings indicate the opportunity for AI to accelerate soil research—the understanding of which can benefit our food and climate systems. Improving our understanding of soils could support more sustainable agriculture, better soil management, and stronger climate adaptation by helping land managers detect nutrient loss, water stress, compaction, and erosion earlier.”
He noted the system’s capacity for perceptual processing, strategic planning, and scientific reasoning, underscoring significant global implications for soil as a critical but undervalued resource.
Bridging AI and Human Expertise
Despite the promising role of AI, challenges such as data quality, transparency, and ethical considerations remain. Dr Mercedes Román Dobarco from the Basque Institute for Agricultural Research and Development (NEIKER), Spain, remarked: “While the use cases are clearly persuasive, and though AI can emulate some aspects of expert reasoning, it cannot replace the contextual judgment, creativity, and critical interpretation scientists bring to research. AI agents also pose challenges around data quality, interpretability, creativity, and dataset bias, particularly without human oversight and domain expertise.”
“Given these limitations, we should treat AI as an augmentative tool that enhances, not replaces, human scientific work,” she concluded.
The paper also discusses AI’s ability to accelerate both ‘fast’ and ‘slow’ science, allowing researchers to focus on foundational understanding and fieldwork while maintaining scientific rigor. Prof McBratney emphasized the importance of interdisciplinary collaboration and ethical considerations to fully realize AI’s potential in soil science.
“Soils are among our planet’s most vital and existential resources. To fully benefit from AI-enhanced soil science, we must embrace interdisciplinary collaboration, ensure equitable access to AI tools, and thoughtfully address the ethical challenges we have outlined. By bridging digital innovation with real-world application, as well as non-negotiable human oversight, AI can supercharge soil science—but only if human knowledge keeps pace. Striking that balance can help us unlock new levels of stewardship and security for soil.”
The article is part of the Frontiers in Science multimedia article hub ‘Multi-agent AI for soil science‘. The hub features an editorial, viewpoint, policy outlook, and a version of the article for kids, from other eminent experts: Prof Jagdish Kumar Ladha (University of California, Davis, USA), Dr Madlene Nussbaum (Utrecht University, Netherlands), and Dr Catherine Nakalembe (University of Maryland, USA).
About
Frontiers in Science is Frontiers’ flagship, multidisciplinary, open access journal focused on transformational science accelerating solutions for healthy lives on a healthy planet.
The journal publishes impactful peer-reviewed lead articles, invited from internationally renowned researchers, on scientific and technological advances addressing global challenges in human and planetary health. These are complemented by unique hubs of multi-audience content that create bridges between researchers, decision-makers, innovators, and the public—empowering people across all areas of science, policy, and society to share and build on these advances.
Reflecting its mission, Frontiers in Science has a panoramic scope encompassing human health and well-being, climate change, ecology and biodiversity, urban development, agriculture, food, water, and energy systems, computing, and social and economic sciences.
For more information, visit www.frontiersin.org/science and follow @FrontScience on X, Frontiers in Science on LinkedIn, and @Frontiers on Bluesky.
REPUBLISHING GUIDELINES: Open access and sharing research is part of Frontiers’ mission. Unless otherwise noted, you can republish articles posted in the Frontiers news site—as long as you include a link back to the original research. Selling the articles is not allowed.
Original Story at www.frontiersin.org