Predicting the adsorption of ammonia nitrogen by biochar in water bodies using machine learning strategies: Model optimization and analysis of key characteristic variables
Environmental Research · 2025-02 · 267 · 120618
DOI: 10.1016/j.envres.2024.120618 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Research, 2025-02. Verfasst von Guixian Xie und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Environmental and Safety Engineering, LiaoNing Petrochemical University, Fushun, 113001, China. Hauptthemen laut MEDLINE: Machine Learning, Charcoal, Ammonia, Water Pollutants, Chemical. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: Department of Education of Liaoning Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
Biochar adsorption technology has been widely used to remove ammonia nitrogen from water bodies. However, existing methods for predicting adsorption efficiency often lack sufficient accuracy and practical usability. This study evaluated eight machine learning models, including XGB, LR, KNN, DT, RF, GBR, SVR, and ANN, to predict the adsorption efficiency of ammonia nitrogen. The evaluation utilized a dataset comprising 770 instances of ammonia nitrogen adsorption by biochar. The models' prediction performances were systematically compared, and cross-validation was applied to enhance their generalization ability, leading to the selection of the best-performing model. The selected model's parameters were further optimized using Bayesian optimization to improve the prediction accuracy. The Bayesian-optimized XGB model achieved the highest predictive performance, with a coefficient of determination (R2) of 0.978. The R2 values of the other models ranged from 0.556 (LR) to 0.927 (RF). Key factors influencing ammonia nitrogen adsorption efficiency were identified using SHAP analysis. These factors included biochar dosage, adsorption time, initial ammonia nitrogen concentration, solution pH, pyrolysis time, and O%. Their optimal ranges were further determined through partial dependency plots. This study developed a reliable machine learning tool for accurately predicting ammonia nitrogen adsorption efficiency. Additionally, it provided insights into optimizing the preparation processes and adsorption conditions of biochar, contributing to its practical application in treating ammonia nitrogen pollution in water bodies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Environmental and Safety Engineering, LiaoNing Petrochemical University, Fushun, 113001, China.
- Jiangsu Environmental Engineering Technology Co., Ltd., Nanjing, 210019, China.
- School of Environmental and Safety Engineering, LiaoNing Petrochemical University, Fushun, 113001, China. Electronic address: mygoddness@163.com.
Förderung
- Department of Education of Liaoning Province
- National Natural Science Foundation of China
Zitieren
APA
Xie, G., Zhu, C., Li, C., Fan, Z., & Wang, B. (2025). Predicting the adsorption of ammonia nitrogen by biochar in water bodies using machine learning strategies: Model optimization and analysis of key characteristic variables. Environmental Research, 267, 120618. https://doi.org/10.1016/j.envres.2024.120618
Vancouver
Xie G, Zhu C, Li C, Fan Z, Wang B. Predicting the adsorption of ammonia nitrogen by biochar in water bodies using machine learning strategies: Model optimization and analysis of key characteristic variables. Environmental Research. 2025;267:120618. doi:10.1016/j.envres.2024.120618
BibTeX
@article{Xie2025,
author = {Xie, Guixian and Zhu, Chi and Li, Chen and Fan, Zhiping and Wang, Bo},
title = {Predicting the adsorption of ammonia nitrogen by biochar in water bodies using machine learning strategies: Model optimization and analysis of key characteristic variables},
journal = {Environmental Research},
year = {2025},
volume = {267},
pages = {120618},
doi = {10.1016/j.envres.2024.120618}
}
EUVIMED