Machine learning application for predicting key properties of activated carbon produced from lignocellulosic biomass waste with chemical activation

Rongge Zou; Zhibin Yang; Jiahui Zhang; Ryan Lei; William Zhang; Fitria Fnu; Daniel C.W. Tsang; Joshua Heyne; Xiao Zhang; Roger Ruan; Hanwu Lei

doi:10.1016/j.biortech.2024.130624

Machine learning application for predicting key properties of activated carbon produced from lignocellulosic biomass waste with chemical activation

Rongge Zou, Zhibin Yang, Jiahui Zhang, Ryan Lei, William Zhang, Fitria Fnu, Daniel C.W. Tsang, Joshua Heyne, Xiao Zhang, Roger Ruan, Hanwu Lei

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

The successful application of gradient boosting regression (GBR) in machine learning to forecast surface area, pore volume, and yield in biomass-derived activated carbon (AC) production underscores its potential for enhancing manufacturing processes. The GBR model, collecting 17 independent variables for two-step activation (2-SA) and 14 for one-step activation (1-SA), demonstrates effectiveness across three datasets—1-SA, 2-SA, and a combined dataset. Notably, in 1-SA, the GBR model yields R² values of 0.76, 0.90, and 0.83 for TPV, yield, and SSA respectively, and records R² of 0.90 and 0.91 for yield in 2-SA and combined datasets. The model highlights the significance of the soaking procedure alongside activation temperature in shaping AC properties with 1-SA or 2-SA, illustrating machine learning's potential in optimizing AC production processes.

Original language	English
Article number	130624
Journal	Bioresource Technology
Volume	399
DOIs	https://doi.org/10.1016/j.biortech.2024.130624
State	Published - May 2024
Externally published	Yes

Funding

This work is funded by the National Institute of Food and Agriculture (NIFA), United States Department of Agriculture (USDA) through the Agriculture and Food Research Initiative (AFRI) that is a leading competitive grants program (Grant no. 2016-67021-24533 and 2018-67009-27904). We would also like to thank Dr. Yunpu Wang from Nanchang University for his kind supports.

Keywords

Activated biochar
Environmental remediation
Machine learning
Surface area
Sustainable waste management
Total pore volume

Access to Document

10.1016/j.biortech.2024.130624

Cite this

@article{6db7db67c1dc423a9f84df114641609f,

title = "Machine learning application for predicting key properties of activated carbon produced from lignocellulosic biomass waste with chemical activation",

abstract = "The successful application of gradient boosting regression (GBR) in machine learning to forecast surface area, pore volume, and yield in biomass-derived activated carbon (AC) production underscores its potential for enhancing manufacturing processes. The GBR model, collecting 17 independent variables for two-step activation (2-SA) and 14 for one-step activation (1-SA), demonstrates effectiveness across three datasets—1-SA, 2-SA, and a combined dataset. Notably, in 1-SA, the GBR model yields R2 values of 0.76, 0.90, and 0.83 for TPV, yield, and SSA respectively, and records R2 of 0.90 and 0.91 for yield in 2-SA and combined datasets. The model highlights the significance of the soaking procedure alongside activation temperature in shaping AC properties with 1-SA or 2-SA, illustrating machine learning's potential in optimizing AC production processes.",

keywords = "Activated biochar, Environmental remediation, Machine learning, Surface area, Sustainable waste management, Total pore volume",

author = "Rongge Zou and Zhibin Yang and Jiahui Zhang and Ryan Lei and William Zhang and Fitria Fnu and Tsang, {Daniel C.W.} and Joshua Heyne and Xiao Zhang and Roger Ruan and Hanwu Lei",

note = "Publisher Copyright: {\textcopyright} 2024 Elsevier Ltd",

year = "2024",

month = may,

doi = "10.1016/j.biortech.2024.130624",

language = "English",

volume = "399",

journal = "Bioresource Technology",

issn = "0960-8524",

publisher = "Elsevier",

}

TY - JOUR

T1 - Machine learning application for predicting key properties of activated carbon produced from lignocellulosic biomass waste with chemical activation

AU - Zou, Rongge

AU - Yang, Zhibin

AU - Zhang, Jiahui

AU - Lei, Ryan

AU - Zhang, William

AU - Fnu, Fitria

AU - Tsang, Daniel C.W.

AU - Heyne, Joshua

AU - Zhang, Xiao

AU - Ruan, Roger

AU - Lei, Hanwu

PY - 2024/5

Y1 - 2024/5

N2 - The successful application of gradient boosting regression (GBR) in machine learning to forecast surface area, pore volume, and yield in biomass-derived activated carbon (AC) production underscores its potential for enhancing manufacturing processes. The GBR model, collecting 17 independent variables for two-step activation (2-SA) and 14 for one-step activation (1-SA), demonstrates effectiveness across three datasets—1-SA, 2-SA, and a combined dataset. Notably, in 1-SA, the GBR model yields R2 values of 0.76, 0.90, and 0.83 for TPV, yield, and SSA respectively, and records R2 of 0.90 and 0.91 for yield in 2-SA and combined datasets. The model highlights the significance of the soaking procedure alongside activation temperature in shaping AC properties with 1-SA or 2-SA, illustrating machine learning's potential in optimizing AC production processes.

AB - The successful application of gradient boosting regression (GBR) in machine learning to forecast surface area, pore volume, and yield in biomass-derived activated carbon (AC) production underscores its potential for enhancing manufacturing processes. The GBR model, collecting 17 independent variables for two-step activation (2-SA) and 14 for one-step activation (1-SA), demonstrates effectiveness across three datasets—1-SA, 2-SA, and a combined dataset. Notably, in 1-SA, the GBR model yields R2 values of 0.76, 0.90, and 0.83 for TPV, yield, and SSA respectively, and records R2 of 0.90 and 0.91 for yield in 2-SA and combined datasets. The model highlights the significance of the soaking procedure alongside activation temperature in shaping AC properties with 1-SA or 2-SA, illustrating machine learning's potential in optimizing AC production processes.

KW - Activated biochar

KW - Environmental remediation

KW - Machine learning

KW - Surface area

KW - Sustainable waste management

KW - Total pore volume

UR - http://www.scopus.com/inward/record.url?scp=85189558909&partnerID=8YFLogxK

U2 - 10.1016/j.biortech.2024.130624

DO - 10.1016/j.biortech.2024.130624

M3 - Article

C2 - 38521172

AN - SCOPUS:85189558909

SN - 0960-8524

VL - 399

JO - Bioresource Technology

JF - Bioresource Technology

M1 - 130624

ER -

Machine learning application for predicting key properties of activated carbon produced from lignocellulosic biomass waste with chemical activation

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this