EUVIMEDEUVIMED entdecken
Crossref

From Prediction to Insight: Explainable Ensemble Learning for CO2-to-Methanol Conversion

Du Nguyen, M. Olga Guerrero-Pérez, Enrique Rodríguez-Castellón, Minh Thien Nguyen, Viet Dung Tran, Thanh Hai Truong, Xuan Phuong Nguyen, Anh Tuan Hoang

ACS Sustainable Chemistry ဦ Engineering · 17.08.2026 · 14 (32) · 14256-14274

DOI: 10.1021/acssuschemeng.6c03657 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Sustainable Chemistry ဦ Engineering, online erschienen am 04.08.2026. Verfasst von Du Nguyen und 7 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Gefördert von: Ministerio de Ciencia, Innovaci?n y Universidades, European Regional Development Fund, Fundaci?n Unicaja.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This work introduced an interpretable machine learning framework for the predictive modeling of CO2 hydrogenation performance for methanol production using the Extra Trees Regression, Histogram Gradient Boosting, and CatBoost algorithms, in terms of CO2 conversion efficiency, methanol selectivity, and CO selectivity. Among the approaches evaluated, Extra Trees demonstrated superior performance for predicting methanol and CO selectivity, whereas Histogram-based Gradient Boosting regression exhibited slightly better generalization for CO2 conversion efficiency. Furthermore, SHAP analysis showed that temperature was the most critical parameter with the highest absolute mean SHAP values for all targets and high nonlinearity. Dependence plots also showed a positive thermal promotion of CO2 conversion and CO selectivity, with a decrease in methanol selectivity at higher temperatures. More importantly, Monte Carlo simulations were performed to quantify predictive uncertainty, and the uncertainty bands spanning 5 to 95% of the model predictions were found to be 15.1%, 41.5%, and 45.9% for conversion, methanol selectivity, and CO selectivity, respectively. Hold-out validation of the models was confirmed by residuals randomly distributed around a mean of zero. Generally, the integrated modeling and explainability framework provides a reliable, transparent, and uncertainty-aware method for accelerating catalyst optimization and the operational strategy development in CO2 valorization systems.

Förderung

  • Ministerio de Ciencia, Innovaci?n y Universidades
  • European Regional Development Fund
  • Fundaci?n Unicaja

Zitieren

APA

Nguyen, D., Guerrero-Pérez, M. O., Rodríguez-Castellón, E., Nguyen, M. T., Tran, V. D., Truong, T. H., Nguyen, X. P., & Hoang, A. T. (2026). From Prediction to Insight: Explainable Ensemble Learning for CO2-to-Methanol Conversion. ACS Sustainable Chemistry ဦ Engineering, 14(32), 14256-14274. https://doi.org/10.1021/acssuschemeng.6c03657

Vancouver

Nguyen D, Guerrero-Pérez MO, Rodríguez-Castellón E, Nguyen MT, Tran VD, Truong TH, et al. From Prediction to Insight: Explainable Ensemble Learning for CO2-to-Methanol Conversion. ACS Sustainable Chemistry ဦ Engineering. 2026;14(32):14256-14274. doi:10.1021/acssuschemeng.6c03657

BibTeX
@article{Nguyen2026,
  author = {Nguyen, Du and Guerrero-Pérez, M. Olga and Rodríguez-Castellón, Enrique and Nguyen, Minh Thien and Tran, Viet Dung and Truong, Thanh Hai and Nguyen, Xuan Phuong and Hoang, Anh Tuan},
  title = {From Prediction to Insight: Explainable Ensemble Learning for CO2-to-Methanol Conversion},
  journal = {ACS Sustainable Chemistry ဦ Engineering},
  year = {2026},
  volume = {14},
  number = {32},
  pages = {14256--14274},
  doi = {10.1021/acssuschemeng.6c03657}
}
Kostenlos starten →