An interpretable ensemble machine learning model for predicting carbon dioxide adsorption on magnesium oxide-based sorbents
Environmental Research · 2026-05 · 297 · 124126
DOI: 10.1016/j.envres.2026.124126 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Research, 2026-05. Verfasst von Lin Fan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Engineering Training Centre, Liaoning Petrochemical University, Fushun, 113001, Liaoning, China; School of Mechanical Engineering, Shenyang Universit…. Hauptthemen laut MEDLINE: Carbon Dioxide, Magnesium Oxide, Machine Learning, Models, Chemical. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: Liaoning Province Educational Department.
Abstract (Originalsprache)
Accurately predicting the carbon dioxide (CO2) adsorption capacity of magnesium oxide (MgO)-based sorbents is crucial for advancing carbon capture technologies. This study develops an interpretable machine learning framework to address this challenge. Fourteen candidate models were evaluated, with six top-performing ones selected for Bayesian hyperparameter optimization using the Optuna framework. A novel weighted ensemble model was then constructed by integrating the entropy weight method and the Technique for Order Preference by Similarity to Ideal Solution. The optimized ensemble model demonstrated outstanding performance on an independent test set, achieving an R2 of 0.9903 with MSE, RMSE, and MAE of 0.361, 0.6008, and 0.2544 respectively, surpassing most individual models. SHapley Additive exPlanations analysis identified material morphology as the most significant feature (43.8% contribution), particularly granular morphology. Process parameters including time (23.3%) and temperature (14.1%) were the next major contributors, while pore structure variables collectively contributed 15.3%. The analysis further revealed complex non-linear dependencies and interaction effects, with the combination of medium temperature (200-400 °C) and adsorption time (100-250 min) proving optimal. Additionally, a web application was deployed to provide real-time prediction capability. This work provides both a reliable predictive tool and valuable mechanistic insights for designing high-performance MgO-based CO2 adsorbents.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Engineering Training Centre, Liaoning Petrochemical University, Fushun, 113001, Liaoning, China; School of Mechanical Engineering, Shenyang University of Technology, Shenyang, 110870, Liaoning, China.
- School of Mechanical Engineering, Liaoning Petrochemical University, Fushun, 113001, Liaoning, China. Electronic address: 1422017226@qq.com.
- Engineering Training Centre, Liaoning Petrochemical University, Fushun, 113001, Liaoning, China.
- School of Mechanical Engineering, Liaoning Petrochemical University, Fushun, 113001, Liaoning, China.
Förderung
- Liaoning Province Educational Department
Zitieren
APA
Fan, L., He, Y., Mo, Y., & Cao, Y. (2026). An interpretable ensemble machine learning model for predicting carbon dioxide adsorption on magnesium oxide-based sorbents. Environmental Research, 297, 124126. https://doi.org/10.1016/j.envres.2026.124126
Vancouver
Fan L, He Y, Mo Y, Cao Y. An interpretable ensemble machine learning model for predicting carbon dioxide adsorption on magnesium oxide-based sorbents. Environmental Research. 2026;297:124126. doi:10.1016/j.envres.2026.124126
BibTeX
@article{Fan2026,
author = {Fan, Lin and He, Yan and Mo, Yunfeng and Cao, Yiming},
title = {An interpretable ensemble machine learning model for predicting carbon dioxide adsorption on magnesium oxide-based sorbents},
journal = {Environmental Research},
year = {2026},
volume = {297},
pages = {124126},
doi = {10.1016/j.envres.2026.124126}
}
EUVIMED