EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Task Gaussian Process Prediction of Pretreatment-Induced Compositional Changes in Kenaf Core Under Data-Limited Conditions

Hao Xu, Yitong Niu, Ying Ying Tye, Chee Keong Lee, Cheu Peng Leh

Catalysts · 10.11.2026 · 16 (11) · 997

DOI: 10.3390/catal16110997 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Catalysts, online erschienen am 10.11.2026. Verfasst von Hao Xu und 4 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Malaysia Ministry of Higher Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pretreatment-induced compositional changes in lignocellulosic biomass are difficult to predict when experimental datasets are small and heterogeneous. This study applied multi-task Gaussian process regression (MTGPR) to jointly predict cellulose, hemicellulose, and lignin contents from residence time, temperature, and initial pH for 31 kenaf-core samples across autohydrolysis, dilute-acid, and alkaline pretreatment. MTGPR attained the lowest mean per-component RMSE under leave-one-out cross-validation (2.54 percentage points), 18% below independently fitted single-task GPRs (3.09 percentage points) and 8% below a response-surface model (2.77 percentage points), while matching the strongest single-task learner, random forest (2.61 percentage points). A diagonal-B ablation yielded 2.51 percentage points, showing that this gain stems from joint fitting with a shared kernel rather than from the explicit cross-task covariance term. At support = 8, a simple route-mean baseline outperformed all learned models, and under leave-one-route-out validation no learned model surpassed the route-mean reference. Cross-conformal intervals restored coverage to 99.5% but at ±7.38 percentage points half-width, which is over-conservative for decision-making. Joint fitting is therefore beneficial relative to independent fitting under data scarcity, but the benefit derives from shared structure rather than cross-task correlation, it does not extend to unseen pretreatment routes, and the uncertainty estimates still require recalibration.

Förderung

  • Malaysia Ministry of Higher Education

Zitieren

APA

Xu, H., Niu, Y., Tye, Y. Y., Lee, C. K., & Leh, C. P. (2026). Multi-Task Gaussian Process Prediction of Pretreatment-Induced Compositional Changes in Kenaf Core Under Data-Limited Conditions. Catalysts, 16(11), 997. https://doi.org/10.3390/catal16110997

Vancouver

Xu H, Niu Y, Tye YY, Lee CK, Leh CP. Multi-Task Gaussian Process Prediction of Pretreatment-Induced Compositional Changes in Kenaf Core Under Data-Limited Conditions. Catalysts. 2026;16(11):997. doi:10.3390/catal16110997

BibTeX
@article{Xu2026,
  author = {Xu, Hao and Niu, Yitong and Tye, Ying Ying and Lee, Chee Keong and Leh, Cheu Peng},
  title = {Multi-Task Gaussian Process Prediction of Pretreatment-Induced Compositional Changes in Kenaf Core Under Data-Limited Conditions},
  journal = {Catalysts},
  year = {2026},
  volume = {16},
  number = {11},
  pages = {997},
  doi = {10.3390/catal16110997}
}
Kostenlos starten →