https://doi.org/10.1140/epjs/s11734-026-02180-7
Regular Article
AI-assisted identification of REE-bearing cenospheres in coal fly ash
M.S. Poliakov Institute of Geotechnical Mechanics of the National Academy of Sciences of Ukraine, Dnipro, Ukraine
a
This email address is being protected from spambots. You need JavaScript enabled to view it.
Received:
29
November
2025
Accepted:
29
January
2026
Published online:
18
February
2026
Abstract
This study applies an integrated analytical and machine-learning clustering approach to characterize fly ash cenospheres – hollow aluminosilicate microspheres considered potential hosts for rare earth elements (REEs). Fly ash from the Prydniprovska Thermal Power Plant (Ukraine) was analyzed using SEM–EDS microchemical imaging and bulk ICP–MS quantification, yielding total REE concentrations of ΣREE = 429.5 ppm, dominated by light REEs (ΣLREE = 332.1 ppm; ΣHREE = 97.4 ppm). Thirty representative cenospheres were examined to obtain major-element compositions (Al, Si, Fe, Ti) and particle diameters. Unsupervised k-means clustering (k = 3) applied to standardized variables identified three morphochemical subtypes with moderate internal separation (silhouette score = 0.29). ANOVA confirmed Ti, Fe, and Si as statistically significant discriminant variables (p < 10⁻4), while Al showed weaker discrimination (p ≈ 0.03) and particle diameter was not significant (p > 0.3). By integrating particle morphometry with major-element chemistry at the individual-particle scale, this approach extends beyond conventional bulk or single-attribute clustering and provides a data-oriented means of distinguishing cenospheres relevant for REE-focused recovery. Although particle-scale REE contents were not quantified, the bulk enrichment of REEs and their preferential incorporation into aluminosilicate matrices suggest that the Al-rich subtype may represent a conceptually promising target for selective beneficiation.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature 2026
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
