EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Compressive-Strength Prediction and Generalization of Solid-Waste Alkali-Activated Materials Under Multi-Source Data Heterogeneity

Yinbo Zhang, Rui He, Xingyang Gao, Wei Chen, Xuanxi Li

Materials · 19.11.2026 · 19 (22) · 4894

DOI: 10.3390/ma19224894 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 19.11.2026. Verfasst von Yinbo Zhang und 4 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xinjiang Uygur Autonomous Region Two-Zone Science and Technology Development Plan, Xinjiang Uygur Autonomous Region Science and Technology Support for Xinjiang Program, Xinjiang Uygur Autonomous Region “Tianshan Talents” Science and Technology Innovation Leading Talent Training Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Compressive strength in solid-waste-based alkali-activated materials (AAMs) depends on precursor chemistry, activator composition, curing history, age, and specimen geometry, producing substantial heterogeneity in literature-compiled data. This study examines how validation boundaries affect apparent predictive accuracy and reliability. We analyzed 1367 records representing 907 unique mixtures across nine database-defined subdomains. We compared hierarchical feature sets and assessed grouped cross-validation, leave-one-domain-out (LODO), mixture-purged LODO, complete age/geometry hold-outs, within-stratum transfer, and zero-shot external testing. Adding processing and chemistry information raised XGBoost grouped-validation R2 from 0.518 to 0.843. Across five tree-based models, LODO increased RMSE by an average factor of 1.86; purging repeated mixtures reduced pooled R2 from 0.454 to 0.274. In 70 external observations from 12 literature-source groups, zero-shot R2 was −0.289 and RMSE was 16.20 MPa. Across five training–calibration repetitions, nominal 90% split-conformal intervals attained mean external coverage of only 36.3%, while 48.6% exceeded at least one training-feature bound. These findings show why predictive accuracy, input support, and uncertainty coverage must be evaluated together before transferring AAM strength models across data domains.

Förderung

  • Xinjiang Uygur Autonomous Region Two-Zone Science and Technology Development Plan
  • Xinjiang Uygur Autonomous Region Science and Technology Support for Xinjiang Program
  • Xinjiang Uygur Autonomous Region “Tianshan Talents” Science and Technology Innovation Leading Talent Training Program
  • Urumqi “Hongshan Talents” Program

Zitieren

APA

Zhang, Y., He, R., Gao, X., Chen, W., & Li, X. (2026). Compressive-Strength Prediction and Generalization of Solid-Waste Alkali-Activated Materials Under Multi-Source Data Heterogeneity. Materials, 19(22), 4894. https://doi.org/10.3390/ma19224894

Vancouver

Zhang Y, He R, Gao X, Chen W, Li X. Compressive-Strength Prediction and Generalization of Solid-Waste Alkali-Activated Materials Under Multi-Source Data Heterogeneity. Materials. 2026;19(22):4894. doi:10.3390/ma19224894

BibTeX
@article{Zhang2026,
  author = {Zhang, Yinbo and He, Rui and Gao, Xingyang and Chen, Wei and Li, Xuanxi},
  title = {Compressive-Strength Prediction and Generalization of Solid-Waste Alkali-Activated Materials Under Multi-Source Data Heterogeneity},
  journal = {Materials},
  year = {2026},
  volume = {19},
  number = {22},
  pages = {4894},
  doi = {10.3390/ma19224894}
}
Kostenlos starten →