Abstract
Global heavy metal(loid) (HM) pollution in soils threatens food security and human health, yet HM mobility—governed by chemical fractions—remains poorly understood at large scales. Here we develop an eXtreme Gradient Boosting model for classifying soil HM dominant fractions using a globally compiled dataset of 9489 field observations. We show that organic carbon and pH positively affect high-mobility of HMs in soil. Using mercury as a case study, we identify both known and previously unreported high-mobility hotspots. The global map indicates that mercury has high mobility across 17.85% of global regions. Combining population and cropland distribution maps with model predictions shows that an estimated 15.1 million people and 100.9 million hectares of farmland are situated in high-mobility regions, with Asia being disproportionately impacted. This study facilitates the efficient identification of dominant HM fractions on a large scale, providing a critical foundation for developing targeted HM stabilization/solidification strategies.
Similar content being viewed by others
Data availability
The data and code generated in this study are available on Figshare (https://doi.org/10.6084/m9.figshare.29554202)72. The Supplementary Data file, including all source data underlying the figures, is also available via Figshare. Global soil properties data were obtained from SoilGrids version 2.0 (https://soilgrids.org/)34. Global soil Hg concentration is available at Figshare (https://doi.org/10.6084/m9.figshare.26335654.v1)33. Global crop data is available at Figshare (https://doi.org/10.6084/m9.figshare.22491997.v5)44. Global population data is available at Zenodo (https://doi.org/10.5281/zenodo.11179644)45.
References
Bagnall, D. K., Shanahan, J. F., Flanders, A., Morgan, C. L. S. & Honeycutt, C. W. Soil health considerations for global food security. Agron. J. 113, 4581–4589 (2021).
Hou, D. et al. Global soil pollution by toxic metals threatens agriculture and human health. Science 388, 316–321 (2025).
Wei, R. et al. Heavy metal concentrations in rice that meet safety standards can still pose a risk to human health. Commun. Earth Environ. 4, 84 (2023).
Hou, D. et al. Metal contamination and bioremediation of agricultural soils for food safety and sustainability. Nat. Rev. Earth Environ. 1, 366–381 (2020).
Coban, O., De Deyn, G. B. & van der Ploeg, M. Soil microbiota as game-changers in restoration of degraded lands. Science 375, abe0725 (2022).
Yang, Q. et al. A review of soil heavy metal pollution from industrial and agricultural regions in China: Pollution and risk assessment. Sci. Total Environ. 642, 690–700 (2018).
Liu, X. et al. Molecular-level understanding of metal ion retention in clay-rich materials. Nat. Rev. Earth Environ. 3, 461–476 (2022).
Imseng, M. et al. Fate of Cd in Agricultural Soils: A Stable Isotope Approach to Anthropogenic Impact, Soil Formation, and Soil-Plant Cycling. Environ. Sci. Technol. 52, 1919–1928 (2018).
Alloway, B. J. Heavy Metals in Soils: Trace Metals and Metalloids in Soils and Their Bioavailability (Springer, Berlin, 2012).
Zhang, Y. et al. Experimental and molecular simulation study of HCl-modified SiO2 nanofluid in coal wettability. Powder Technol 469, 121887 (2026).
Song, X. et al. Uncovering soil heavy metal pollution hotspots and influencing mechanisms through machine learning and spatial analysis. Environ. Pollut. 370, 125901 (2025).
Zhang, S. et al. Escalating arsenic contamination throughout Chinese soils. Nat. Sustain. 7, 766–775 (2024).
Wang, X. et al. Climate and Vegetation As Primary Drivers for Global Mercury Storage in Surface Soil. Environ. Sci. Technol. 53, 10665–10675 (2019).
Jia, J. et al. Fractionation, source, and ecological risk assessment of heavy metals in cropland soils across a 100-year reclamation chronosequence in an estuary, South China. Sci. Total Environ. 807, 151725 (2022).
Qi, C. et al. Global and regional patterns of soil metal(loid) mobility and associated risks. Nat. Commun. 16, 2947 (2025).
Wieczorek, J., Baran, A. & Bubak, A. Mobility, bioaccumulation in plants, and risk assessment of metals in soils. Sci. Total Environ. 882, 163574 (2023).
Liu, H. et al. Dynamic Behaviors of Newly Deposited Atmospheric Heavy Metals in the Soil-Pak Choi System. Environ. Sci. Technol. 56, 12734–12744 (2022).
Yang, H. et al. Predicting Heavy Metal Adsorption on Soil with Machine Learning and Mapping Global Distribution of Soil Adsorption Capacities. Environ. Sci. Technol. 55, 14316–14328 (2021).
Qi, C. et al. Spectral-Based Machine Learning Enables Rapid and Large-Scale Adsorption Capacity Prediction of Heavy Metals in Soil. ACS ES&T Eng 4, 2657–2667 (2024).
Angon, P. B. et al. Sources, effects and present perspectives of heavy metals contamination: Soil, plants and human food chain. Heliyon 10, e28357 (2024).
Xu, W., Yuan, J. & Zeng, G. Introduction of heavy metals contamination in the water and soil: a review on source, toxicity and remediation methods. Green Chem. Lett. Rev 17, 2404235 (2024).
Li, G., Lu, N., Wei, Y. & Zhu, D. Relationship between Heavy Metal Content in Polluted Soil and Soil Organic Matter and pH in Mining Areas. IOP Conf. Ser.:Mater. Sci. Eng. 394, 052081 (2018).
Król, A., Mizerna, K. & Bożym, M. An assessment of pH-dependent release and mobility of heavy metals from metallurgical slag. J. Hazard. Mater. 384, 121502 (2020).
Basti, S., Sahu, C., Pati, S. S. & Sahu, S. K. Impact of organic carbon on heavy metals of river sediments and aquatic ecosystems: A review. Environ. Qual. Manag. 34, e22253 (2024).
Qu, C. et al. Heavy metal behaviour at mineral-organo interfaces: Mechanisms, modelling and influence factors. Environ. Int. 131, 104995 (2019).
Wu, Y. et al. pH-dependent overestimation of heavy metals mobility risk in soils: Implications for soil quality assessment. J. Hazard. Mater. 501, 140792 (2026).
Caporale, A. G. & Violante, A. Chemical Processes Affecting the Mobility of Heavy Metals and Metalloids in Soil Environments. Curr. Pollut. Rep. 2, 15–27 (2016).
Kyziol, J. Effect of physical properties and cation exchange capacity on sorption of heavy metals onto peats. Pol. J. Environ. Stud. 11 (2002).
Inglezakis, V., Zorpas, A., Loizidou, M. & Grigoropoulou, H. The effect of competitive cations and anions on ion exchange of heavy metals. Sep. Purif. Technol. 46, 202–207 (2005).
William Kajjumba, G., Emik, S., Öngen, A., Kurtulus Özcan, H. & Aydın, S. Modelling of adsorption kinetic processes—Errors, theory and application. In Advanced Sorption Process Applications (ed. Edebali, S.) (IntechOpen, 2019). https://doi.org/10.5772/intechopen.80495.
Gu, S., Kang, X., Wang, L., Lichtfouse, E. & Wang, C. Clay mineral adsorbents for heavy metal removal from wastewater: a review. Environ. Chem. Lett. 17, 629–654 (2019).
Martin, L. A., Wissocq, A., Benedetti, M. F. & Latrille, C. Thallium (Tl) sorption onto illite and smectite: Implications for Tl mobility in the environment. Geochim. Cosmochim. Acta 230, 1–16 (2018).
Guo, W. et al. Warming-Induced Vegetation Greening May Aggravate Soil Mercury Levels Worldwide. Environ. Sci. Technol. 58, 15078–15089 (2024).
Poggio, L. et al. SoilGrids 2.0: producing soil information for the globe with quantified spatial uncertainty. Soil 7, 217–240 (2021).
Soares, L. C., Egreja Filho, F. B., Linhares, L. A., Windmoller, C. C. & Yoshida, M. I. Accumulation and oxidation of elemental mercury in tropical soils. Chemosphere 134, 181–191 (2015).
O’Connor, D. et al. Mercury speciation, transformation, and transportation in soils, atmospheric flux, and implications for risk management: A critical review. Environ. Int. 126, 747–761 (2019).
Chen, L. et al. Global Distribution of Mercury in Foliage Predicted by Machine Learning. Environ. Sci. Technol. 58, 15629–15637 (2024).
Xiao, C. et al. Understanding the Global Distribution of Groundwater Sulfate and Assessing Population at Risk. Environ. Sci. Technol. 58, 21002–21014 (2024).
Ayotte, J. D., Medalie, L., Qi, S. L., Backer, L. C. & Nolan, B. T. Estimating the High-Arsenic Domestic-Well Population in the Conterminous United States. Environ. Sci. Technol. 51, 12443–12454 (2017).
Orgiazzi, A., Ballabio, C., Panagos, P., Jones, A. & Fernández-Ugalde, O. LUCAS Soil, the largest expandable soil dataset for Europe: a review. Eur. J. Soil Sci. 69, 140–153 (2018).
Tørseth, K. et al. Introduction to the European Monitoring and Evaluation Programme (EMEP) and observed atmospheric composition change during 1972–2009. Atmos. Chem. Phys. 12, 5447–5481 (2012).
Lobo Vicente, J. et al. HBM4EU results support the Chemicals’ Strategy for Sustainability and the Zero-Pollution Action Plan. Int. J. Hyg. Environ. Health 248, 114111 (2023).
Panagos, P., Jones, A., Lugato, E. & Ballabio, C. A Soil Monitoring Law for Europe. Glob. Chall. 9, 2400336 (2025).
Tang, F. H. M. et al. CROPGRIDS: a global geo-referenced dataset of 173 crops. Sci. Data 11, 413 (2024).
Liu, L., Cao, X., Li, S. & Jie, N. A 31-year (1990–2020) global gridded population dataset generated by cluster analysis and statistical learning. Sci. Data 11, 124 (2024).
Malasani, C. R. et al. Modeling of mercury deposition in India: evaluating emission inventories and anthropogenic impacts. Environ. Sci.:Processes Impacts 26, 1999–2009 (2024).
Vudamala, K. et al. Comparative Assessment of Heavy Metal Contamination and Pollution Trends in Indian Estuarine Sediments: Insights from East and West Coasts of India. ACS ES&T Water 5, 2760–2777 (2025).
Jetashree, Wicke, B. & Liang, S. Parsing India’s mercury crisis: A socioeconomic take reveals the defining role of domestic consumerism. J. Cleaner Prod. 463, 142742 (2024).
Kumar, A. et al. Mercury in the natural environment: Biogeochemical cycles and associated health risks. J. Geochem. Explor. 267, 107594 (2024).
Sutou, A. & Wang, J. Influence-Balanced XGBoost: Improving XGBoost for Imbalanced Data Using Influence Functions. IEEE Access 12, 193473–193486 (2024).
Rauret, G. et al. Improvement of the BCR three step sequential extraction procedure prior to the certification of new sediment and soil reference materials. J. Environ. Monit. 1, 57–61 (1999).
Kumar, A. K., Mai, N. N., Tian, K. & Xia, Y. Isochronous Temporal Metric for Neighbourhood Analysis in Classification Tasks. SN Comput Sci 4, 807 (2023).
Jiang, Y. et al. Topological representations of crystalline compounds for the machine-learning prediction of materials properties. npj Comput. Mater. 7, 28 (2021).
Shaheen, S. M. & Rinklebe, J. Geochemical fractions of chromium, copper, and zinc and their vertical distribution in floodplain soil profiles along the Central Elbe River, Germany. Geoderma 228-229, 142–159 (2014).
Bogusz, A. & Oleszczuk, P. Sequential extraction of nickel and zinc in sewage sludge- or biochar/sewage sludge-amended soil. Sci. Total Environ. 636, 927–935 (2018).
Ye, J. et al. New magnetic proxies to reveal source and bioavailability of heavy metals in contaminated soils. J. Hazard. Mater. 479, 135665 (2024).
Chen, M. et al. Unstable geogenic arsenic in reclaimed coastal soils poses environmental risks. Commun. Earth Environ. 6, 633 (2025).
Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Theng, D. & Bhoyar, K. K. Feature selection techniques for machine learning: a survey of more than two decades of research. Knowl. Inf. Syst. 66, 1575–1637 (2024).
Sharma, A. & Singh, M. Batch reinforcement learning approach using recursive feature elimination for network intrusion detection. Eng. Appl. Artif. Intel. 136, 109013 (2024).
Chennamaneni, P. R., Echambadi, R., Hess, J. D. & Syam, N. Diagnosing harmful collinearity in moderated regressions: A roadmap. Int. J. Res. Mark. 33, 172–182 (2016).
Luo, J., Yuan, Y. & Xu, S. Improving GBDT performance on imbalanced datasets: An empirical study of class-balanced loss functions. Neurocomputing 634, 129896 (2025).
Zhang, N. et al. Geochemical-integrated machine learning approach predicts the distribution of cadmium speciation in European and Chinese topsoils. Commun. Earth Environ. 6, 548 (2025).
Qi, X. et al. Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants. Redox Biology 79, 103470 (2025).
Hu, T. et al. Classification of arsenic contamination in soil across the EU by vis-NIR spectroscopy and machine learning. Int. J. Appl. Earth. Obs. 134, 104158 (2024).
Driscoll, C. T., Mason, R. P., Chan, H. M., Jacob, D. J. & Pirrone, N. Mercury as a Global Pollutant: Sources, Pathways, and Effects. Environ. Sci. Technol. 47, 4967–4983 (2013).
Zhou, J., Obrist, D., Dastoor, A., Jiskra, M. & Ryjkov, A. Vegetation uptake of mercury and impacts on global cycling. Nat. Rev. Earth Environ. 2, 269–284 (2021).
Dastoor, A. et al. Arctic mercury cycling. Nat. Rev. Earth Environ. 3, 270–286 (2022).
Landis, J. D. et al. Quantifying soil accumulation of atmospheric mercury using fallout radionuclide chronometry. Nat. Commun. 15, 5430 (2024).
Peng, D. et al. Human perturbations to mercury in global rivers. Sci. Adv. 11, eadw0471.
van den Hoogen, J. et al. Soil nematode abundance and functional group composition at a global scale. Nature 572, 194–198 (2019).
Hu, T. et al. Figshare. https://doi.org/10.6084/m9.figshare.29554202 (2025).
Acknowledgements
This work was supported by National Natural Science Foundation of China (No. 22376221 and No. 22176223), Natural Science Foundation of Hunan Province, China (No. 2024JJ2074), and Young Elite Scientists Sponsorship Program by CAST (No. 2023QNRC001). This work was partly supported by the High Performance Computing Center of Central South University.
Author information
Authors and Affiliations
Contributions
T.H., and C.C.Q. designed the project. T.H., C.C.Q., and M.T.W. constructed the modeling methodology and performed the modeling. L.Y.C., and Q.S.C. participated in results analysis and discussion. T.H. wrote the initial draft of the manuscript, and all authors edited the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests
Peer review
Peer review information
Communications Earth & Environment thanks Abiot Molla and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Primary Handling Editors: Sadia Ilyas and Somaparna Ghosh. A peer review file is available.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Hu, T., Wu, M., Chen, Q. et al. Machine learning uncovers dominant fractions of heavy metal(loid)s in global soils. Commun Earth Environ (2026). https://doi.org/10.1038/s43247-026-03221-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s43247-026-03221-8
