Rough set machine learning-based model for prediction of deep eutectic solvent pretreatment of lignocellulosic biomass
Authors:
Open Access
- 13 June 2025
- journal article
- research article
- Published by Springer Nature in Clean Technologies and Environmental Policy
- Vol. 27 (11) , 6459-6477
Abstract
Recently, deep eutectic solvents (DES) have shown promising results for its application in the pretreatment of lignocellulosic biomass (LCB) to produce fermentable sugars. The optimal pretreatment conditions have been determined through predictive models developed from machine learning algorithms. These models, however, are black box models where the results cannot reveal the scientific reasons behind the identified relationships. To address such limitations, this work employed rough set machine learning (RSML) to create an accurate and interpretable predictive model capable of analysing DES efficiency in pretreating LCB. RSML generates results represented as if–then rules by learning from a dataset composed of conditional and decision attributes. The selected conditional attributes are DES composition, LCB properties (including type and composition of biomass), and pretreatment conditions, while sugar yield is the decision attribute. The RSML model possesses 94.5% and 90.3% predictive ability when applied to validation set and testing set, respectively, recommending that to achieve sugar yield above 75%, high temperature (> 105 °C), low DES-to-biomass ratio (< 5.8), and short duration (< 2.25 h), and acid-based DES are required. Graphical AbstractKeywords
Funding Information
- Malaysia Ministry of Higher Education (FRGS/1/2024/TK05/HWUM/03/1, FRGS/1/2024/TK05/HWUM/03/1, FRGS/1/2024/TK05/HWUM/03/1, FRGS/1/2024/TK05/HWUM/03/1)
This publication has 69 references indexed in Scilit:
- Machine Learning Modelling for Predicting the Efficacy of Ionic Liquid-Aided Biomass PretreatmentBioEnergy Research, 2024
- Application of waste biomass for the production of biofuels and catalysts: a reviewClean Technologies and Environmental Policy, 2024
- Interpreting Black-Box Models: A Review on Explainable Artificial IntelligenceCognitive Computation, 2023
- Estimation of fast pyrolysis bio‐oil properties from feedstock characteristics using rough‐set ‐based machine learningInternational Journal of Energy Research, 2022
- A review on key pretreatment approaches for lignocellulosic biomass to produce biofuel and value-added productsInternational Journal of Environmental Science and Technology, 2022
- Enhanced cellulase accessibility using acid-based deep eutectic solvent in pretreatment of empty fruit bunchesCellulose, 2019
- Prediction of CO2 storage site integrity with rough set-based machine learningClean Technologies and Environmental Policy, 2019
- Fruit peels support higher yield and superior quality bacterial cellulose productionApplied Microbiology and Biotechnology, 2015
- Toward an aggregated understanding of enzymatic hydrolysis of cellulose: Noncomplexed cellulase systemsBiotechnology and Bioengineering, 2004
- Ethanol from lignocellulosic biomass: Technology, economics, and opportunitiesBioresource Technology, 1994