Integrated machine learning and response surface methodology for screening and optimization of high-performance Mg-modified bamboo biochar for phosphorus adsorption in water
{"title":"Integrated machine learning and response surface methodology for screening and optimization of high-performance Mg-modified bamboo biochar for phosphorus adsorption in water","authors":"Yuheng Han, Lingzhi Zhu, Xiaoran Li, Dongxu Cui, Jinjin Li, Kehui Cen, Dengyu Chen","doi":"10.1016/j.indcrop.2025.121213","DOIUrl":null,"url":null,"abstract":"<div><div>Biochar adsorption is an effective method for removing excessive phosphorus from water bodies. In this study, the phosphorus adsorption capacity of biochar was investigated using a machine learning (ML) approach. A dataset consisting of 762 previously published data points from 122 types of biochar was analyzed, with the Random Forest model yielding the best performance (test <em>R</em>² = 0.98, test RMSE = 13.79). The predictions were validated through conducting laboratory experiments on 17 Mg-modified bamboo biochar samples (<em>R</em>² = 0.97, RMSE = 2.8, <em>Q</em><sub>max</sub> = 235.31 mg/g). The optimal preparation conditions were found to be a pyrolysis temperature of 700 °C, pyrolysis time of 3 h, and MgCl<sub>2</sub> concentration of 3 mol/L. X-ray photoelectron spectroscopy confirmed that adsorption performance is positively correlated with Mg content. Kinetic and isotherm tests (Langmuir <em>Q</em><sub>max</sub> = 240.55 mg/g) further supported these findings, providing insights for the preparation of high-performance Mg-modified bamboo biochar.</div></div>","PeriodicalId":13581,"journal":{"name":"Industrial Crops and Products","volume":"231 ","pages":"Article 121213"},"PeriodicalIF":5.6000,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Industrial Crops and Products","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0926669025007599","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURAL ENGINEERING","Score":null,"Total":0}
引用次数: 0
Abstract
Biochar adsorption is an effective method for removing excessive phosphorus from water bodies. In this study, the phosphorus adsorption capacity of biochar was investigated using a machine learning (ML) approach. A dataset consisting of 762 previously published data points from 122 types of biochar was analyzed, with the Random Forest model yielding the best performance (test R² = 0.98, test RMSE = 13.79). The predictions were validated through conducting laboratory experiments on 17 Mg-modified bamboo biochar samples (R² = 0.97, RMSE = 2.8, Qmax = 235.31 mg/g). The optimal preparation conditions were found to be a pyrolysis temperature of 700 °C, pyrolysis time of 3 h, and MgCl2 concentration of 3 mol/L. X-ray photoelectron spectroscopy confirmed that adsorption performance is positively correlated with Mg content. Kinetic and isotherm tests (Langmuir Qmax = 240.55 mg/g) further supported these findings, providing insights for the preparation of high-performance Mg-modified bamboo biochar.
期刊介绍:
Industrial Crops and Products is an International Journal publishing academic and industrial research on industrial (defined as non-food/non-feed) crops and products. Papers concern both crop-oriented and bio-based materials from crops-oriented research, and should be of interest to an international audience, hypothesis driven, and where comparisons are made statistics performed.