Enhancing soil science research with multi-agent artificial intelligence systems
4 affiliations
- 1School of Life and Environmental Sciences, Sydney Institute of Agriculture, The University of Sydney
- 2Department of Soil Science, Luiz de Queiroz College of Agriculture, University of São Paulo
- 3Department of Conservation of Natural Resources, Basque Institute for Agricultural Research and Development (NEIKER), Basque Research and Technology Alliance (BRTA)
- 4Institute of Biological & Environmental Sciences, University of Aberdeen
Abstract
Soil science is entering a new era characterized by the integration of artificial intelligence (AI) multi-agent systems, extending the field beyond traditional machine learning (ML) applications such as digital soil mapping and spectroscopy. While current ML tools are effective for specific tasks, they often lack the reasoning, contextual integration, and adaptability required to address complex, dynamic soil systems. We propose multi-agent AI systems—autonomous, interactive software agents capable of perceptual processing, planning, and scientific reasoning—as a novel framework to support and accelerate soil science research. These agents can fulfill diverse roles, including synthesizing data from field sensors and remote sensing to create dynamic digital soil twins, generating hypotheses, designing experiments, and simulating climate-driven changes in soil function. To illustrate this approach, we tasked a multi-agent system with creating research hypotheses on the topic of mineral-associated organic carbon saturation in soils. The agents generated five hypotheses on effective versus theoretical saturation thresholds, biological and chemical controls, climate influence, interdisciplinary feedback, and actionable management strategies. Each hypothesis was evaluated for empirical grounding, conceptual breadth, and scientific rigor by experts and a simulated peer review. Our findings highlight the potential of multi-agent AI systems, guided by human experts, to accelerate early-stage discovery, support interdisciplinary exploration, and emulate the scientific review process. Nonetheless, challenges remain, particularly around data quality, model transparency, epistemic overtrust, computational cost, ethical implications, and the retention of foundational scientific knowledge. We emphasize AI as an augmentative partner, not a replacement, for human-led discovery.
Related
- Artificial Intelligence for Blue Transformation: A Review of Predictive Modeling and Decision Support Systems in Sustainable Aquaculture
- 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
- Trends in soil organic carbon prediction research using geospatial technologies and artificial intelligence: an exploratory bibliometric analysis (2005-2025)
- Exploring data science as a tool to advance linked socioecological systems in the context of climate change
- Green Microbiology for Planetary Resilience: A Research Agenda for Microbial Sustainability Science.
BibTeX
@article{minasny2026enhancing,
title = {{Enhancing soil science research with multi-agent artificial intelligence systems}},
author = {Budiman Minasny and Alex McBratney and José Alexandre Melo Demattê and Mercedes Román Dobarco and Pete Smith},
journal = {Frontiers in Science},
year = {2026},
month = may,
doi = {10.3389/fsci.2026.1721295},
url = {https://doi.org/10.3389/fsci.2026.1721295},
note = {CC BY},
}
RIS
TY - JOUR
TI - Enhancing soil science research with multi-agent artificial intelligence systems
AU - Budiman Minasny
AU - Alex McBratney
AU - José Alexandre Melo Demattê
AU - Mercedes Román Dobarco
AU - Pete Smith
PY - 2026
DA - 2026/05/21
JO - Frontiers in Science
DO - 10.3389/fsci.2026.1721295
UR - https://doi.org/10.3389/fsci.2026.1721295
AB - Soil science is entering a new era characterized by the integration of artificial intelligence (AI) multi-agent systems, extending the field beyond traditional machine learning (ML) applications such as digital soil mapping and spectroscopy. While current ML tools are effective for specific tasks, they often lack the reasoning, contextual integration, and adaptability required to address complex, dynamic soil systems. We propose multi-agent AI systems—autonomous, interactive software agents capable of perceptual processing, planning, and scientific reasoning—as a novel framework to support and accelerate soil science research. These agents can fulfill diverse roles, including synthesizing data from field sensors and remote sensing to create dynamic digital soil twins, generating hypotheses, designing experiments, and simulating climate-driven changes in soil function. To illustrate this approach, we tasked a multi-agent system with creating research hypotheses on the topic of mineral-associated organic carbon saturation in soils. The agents generated five hypotheses on effective versus theoretical saturation thresholds, biological and chemical controls, climate influence, interdisciplinary feedback, and actionable management strategies. Each hypothesis was evaluated for empirical grounding, conceptual breadth, and scientific rigor by experts and a simulated peer review. Our findings highlight the potential of multi-agent AI systems, guided by human experts, to accelerate early-stage discovery, support interdisciplinary exploration, and emulate the scientific review process. Nonetheless, challenges remain, particularly around data quality, model transparency, epistemic overtrust, computational cost, ethical implications, and the retention of foundational scientific knowledge. We emphasize AI as an augmentative partner, not a replacement, for human-led discovery.
SN - 2813-6330
ER -