Machine learning-based prediction of PAHs thermal desorption efficiency: Model optimization, boundary correction, and mechanistic insights
Journal of Environmental Management · 2025
DOI: 10.1016/j.jenvman.2025.127705 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Environmental Management, 2025. Verfasst von Pengcheng Fu und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Chemistry and Chemical Engineering, China University of Petroleum (East China), Qingdao, 266580, Shandong, PR China. Hauptthemen laut MEDLINE: Machine Learning, Polycyclic Aromatic Hydrocarbons, Soil Pollutants. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Xinjiang Uygur Autonomous Region Natural Science Foundation, National Key Research and Development Program of China.
Abstract (Originalsprache)
Accurate prediction of PAHs removal efficiency during thermal desorption remains challenging due to complex nonlinear interactions among soil properties, contaminant characteristics, and operational parameters. To address this, nine machine learning models were developed and optimized to predict PAHs thermal desorption efficiency, incorporating Bayesian hyperparameter tuning, boundary-aware target transformation, and interpretability analysis. A logit-based transformation was applied to ensure the physical plausibility of remediation efficiency [0-100 %] and improve prediction accuracy near the upper boundary (>90 %). Among the tested models, ensemble tree algorithms, particularly the CatBoost model (R2 = 0.9709), achieved the highest accuracy without overfitting. Shapley Additive Explanations and partial dependence analyses revealed that reaction time, temperature, and the boiling point-to-temperature ratio were dominant predictors, while soil moisture and organic matter exhibited dual inhibitory-facilitative roles, confirming two-phase desorption kinetics and threshold-based thermal effects. The optimized models maintained strong generalization in 1200 Monte Carlo validations (R2 > 0.94), and stratified modeling by pollutant species further improved accuracy (R2 > 0.98 for phenanthrene and pyrene). This study establishes a robust and interpretable machine learning framework for optimizing PAHs thermal desorption and provides practical insights for enhancing remediation reliability, energy efficiency, and intelligent process control.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Chemistry and Chemical Engineering, China University of Petroleum (East China), Qingdao, 266580, Shandong, PR China.
- College of Chemistry and Chemical Engineering, China University of Petroleum (East China), Qingdao, 266580, Shandong, PR China. Electronic address: qimeng@upc.edu.cn.
- Jereh New Energy Regeneration and Recycling Technology Co., Ltd., Yantai, 264003, Shandong, PR China.
- College of Chemistry and Chemical Engineering, China University of Petroleum (East China), Qingdao, 266580, Shandong, PR China. Electronic address: zhaodf@vip.sina.com.
Förderung
- Xinjiang Uygur Autonomous Region Natural Science Foundation
- National Key Research and Development Program of China
Zitieren
APA
Fu, P., Qi, M., Liu, C., Zhang, C., Zhao, Y., Liu, Z., Wang, H., & Zhao, D. (2025). Machine learning-based prediction of PAHs thermal desorption efficiency: Model optimization, boundary correction, and mechanistic insights. Journal of Environmental Management. https://doi.org/10.1016/j.jenvman.2025.127705
Vancouver
Fu P, Qi M, Liu C, Zhang C, Zhao Y, Liu Z, et al. Machine learning-based prediction of PAHs thermal desorption efficiency: Model optimization, boundary correction, and mechanistic insights. Journal of Environmental Management. 2025. doi:10.1016/j.jenvman.2025.127705
BibTeX
@article{Fu2025,
author = {Fu, Pengcheng and Qi, Meng and Liu, Chunshuang and Zhang, Cheng and Zhao, Yuhao and Liu, Zhibao and Wang, Hao and Zhao, Dongfeng},
title = {Machine learning-based prediction of PAHs thermal desorption efficiency: Model optimization, boundary correction, and mechanistic insights},
journal = {Journal of Environmental Management},
year = {2025},
doi = {10.1016/j.jenvman.2025.127705}
}
EUVIMED