Interpretable Machine Learning-Guided Optimization of Laser-Driven Photocatalytic Degradation of Tetracycline Hydrochloride over ZnO/Cu1.35O/g-C3N4 Composites
5 affiliations
- 1Intelligent Agriculture Research Institute, Jilin Agricultural University, Changchun 130000, China
- 2Jilin Provincial Science and Technology Innovation Center of Health Products and Medical Materials with Characteristic Resources, Changchun 130000, China
- 3School of Food Science and Engineering, Jilin Agricultural University, Changchun 130000, China
- 4Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130000, China
- 5School of Municipal and Environmental Engineering, Jilin University of Architecture, Changchun 130000, China
Abstract
Laser-driven photocatalysis provides a wavelength-tunable approach for antibiotic removal, but its performance depends on complex interactions among catalyst properties, irradiation parameters, and operating conditions. This study developed an interpretable machine learning-guided framework integrating entropy weight-based evaluation, predictive modeling, and SHAP analysis to investigate the apparent removal efficiency of tetracycline hydrochloride (TCH) over ZnO/Cu1.35O and ZnO/Cu1.35O/g-C3N4 composites under red, blue, and mixed laser irradiation. At an initial TCH concentration of 20 mg L−1, entropy weight analysis identified 0.02 g ZnO/Cu1.35O under red laser irradiation at 50 μmol m−2 s−1 as the highest-scoring scheme (0.73). At 30 mg L−1, ZCG-3 under mixed red/blue laser irradiation at 200 μmol m−2 s−1 achieved the highest score (0.90). Among five machine learning models, CCO-XGBoost exhibited the best average predictive performance under five-fold group-based cross-validation, with a mean R2 of 0.92 ± 0.06 and a mean RMSE of 8.27 ± 2.79%. SHAP analysis identified reaction time, laser intensity, and initial TCH concentration as the most influential predictive features, reflecting model-based associations rather than physicochemical causality. These findings provide a data-driven framework for treatment-scheme evaluation and UV-Vis-derived apparent TCH removal prediction within the investigated experimental domain
Related
- A 2D/2D g-C3N4/BiOBr S-Scheme Heterojunction for Photocatalytic Oxidative Coupling of Benzylamine and Degradation of Tetracycline: Enhanced Charge Separation and Mechanistic Insights
- LaVO4/Bi2O2S S-Scheme Heterojunction Driving Highly Efficient Photocatalytic Degradation of Tetracycline Antibiotics
- Integrated Photocatalytic and Photoelectrocatalytic Degradation of Organic Dyes Over CuV 2 O 6 : Mechanistic Insights and RSM‐Based Optimization
- Machine Learning-Assisted Analysis of Chloride-Enhanced BiOCl/DSA Anode for Synergistic Denitrification and Tetracycline Degradation: Performance, Mechanisms, and Product Regulation
- Innovative AuAg bimetallic nanoparticle synthesis using food waste materials: its biological applications and photocatalytic degradation potentials
BibTeX
@article{li2026interpretable,
title = {{Interpretable Machine Learning-Guided Optimization of Laser-Driven Photocatalytic Degradation of Tetracycline Hydrochloride over ZnO/Cu1.35O/g-C3N4 Composites}},
author = {Weiping Li and Leijinyu Zhou and Shuangshuang Yang and Jiahao Zhang and Jiage Wu and Wenbo Fang and Helong Yu and Zhiqiang Cheng and Lijun Wang and Xuemei Liang and Yuxin Zhao},
journal = {Catalysts},
year = {2026},
month = oct,
doi = {10.3390/catal16110937},
url = {https://www.mdpi.com/2073-4344/16/11/937},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Interpretable Machine Learning-Guided Optimization of Laser-Driven Photocatalytic Degradation of Tetracycline Hydrochloride over ZnO/Cu1.35O/g-C3N4 Composites
AU - Weiping Li
AU - Leijinyu Zhou
AU - Shuangshuang Yang
AU - Jiahao Zhang
AU - Jiage Wu
AU - Wenbo Fang
AU - Helong Yu
AU - Zhiqiang Cheng
AU - Lijun Wang
AU - Xuemei Liang
AU - Yuxin Zhao
PY - 2026
DA - 2026/10/22
JO - Catalysts
DO - 10.3390/catal16110937
UR - https://www.mdpi.com/2073-4344/16/11/937
AB - Laser-driven photocatalysis provides a wavelength-tunable approach for antibiotic removal, but its performance depends on complex interactions among catalyst properties, irradiation parameters, and operating conditions. This study developed an interpretable machine learning-guided framework integrating entropy weight-based evaluation, predictive modeling, and SHAP analysis to investigate the apparent removal efficiency of tetracycline hydrochloride (TCH) over ZnO/Cu1.35O and ZnO/Cu1.35O/g-C3N4 composites under red, blue, and mixed laser irradiation. At an initial TCH concentration of 20 mg L−1, entropy weight analysis identified 0.02 g ZnO/Cu1.35O under red laser irradiation at 50 μmol m−2 s−1 as the highest-scoring scheme (0.73). At 30 mg L−1, ZCG-3 under mixed red/blue laser irradiation at 200 μmol m−2 s−1 achieved the highest score (0.90). Among five machine learning models, CCO-XGBoost exhibited the best average predictive performance under five-fold group-based cross-validation, with a mean R2 of 0.92 ± 0.06 and a mean RMSE of 8.27 ± 2.79%. SHAP analysis identified reaction time, laser intensity, and initial TCH concentration as the most influential predictive features, reflecting model-based associations rather than physicochemical causality. These findings provide a data-driven framework for treatment-scheme evaluation and UV-Vis-derived apparent TCH removal prediction within the investigated experimental domain
SN - 2073-4344
ER -