Moisture content prediction in durian husk biomass via near infrared spectroscopy coupled with aquaphotomics and explainable machine learning

Simple item page
dc.contributor.authorShrestha, Zenisha
dc.contributor.authorShrestha, Bijendra
dc.contributor.authorSirisomboon, Panmanas
dc.contributor.authorPun, Umed Kumar
dc.contributor.authorBajracharya, Tri Ratna
dc.contributor.authorShrestha, Bim Prasad
dc.contributor.authorPornchaloempong, Pimpen
dc.date.accessioned2026-08-06T10:53:16Z
dc.date.available2026-08-06T10:53:16Z
dc.date.issued2025-12-15
dc.description.abstractAccurate determination of moisture content is essential for energy efficiency and biomass management for fuel materials such as durian husk. Traditional methods of determining biomass moisture content are time-consuming and require specialized expertise, posing challenges for continuous monitoring. To address this limitation, this study applies Near Infrared Spectroscopy (NIRS) combined with machine learning models to rapidly and accurately assess moisture content. Both linear Partial Least Squares Regression (PLSR) and non-linear approaches were used, including Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Extreme Gradient Boosting (XGB). The application of preprocessing techniques, notably the Savitzky-Golay second derivative (SD) and Standard Normal Variate (SNV), significantly augmented the predictive performance, highlighting the importance of data preprocessing in spectral analysis. Synthetic spectral augmentation using Gaussian noise revealed that while SVM and ANN exhibited near-perfect performance, SVM demonstrated quantifiable reliability. This study also demonstrates SVM as the most sensitive and reliable method for detecting and quantifying moisture content in durian husk. This research contributes novel insights to biomass analysis, highlighting the benefits of integrating NIRS and feasibility of explainable machine learning techniques to identify water related spectral parameters to advance aquaphotomics, thereby advancing rapid and accurate biomass characterization.
dc.identifier.citationChemometrics and Intelligent Laboratory Systems, 267, 2025
dc.identifier.doi10.1016/j.chemolab.2025.105538
dc.identifier.issn01697439
dc.identifier.other2-s2.0-105016735511
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/17522
dc.sourceChemometrics and Intelligent Laboratory Systems
dc.subjectAquaphotomics
dc.subjectDurian husk biomass
dc.subjectMachine learning
dc.subjectMoisture content
dc.subjectNIR
dc.titleMoisture content prediction in durian husk biomass via near infrared spectroscopy coupled with aquaphotomics and explainable machine learning
dc.typeArticle

Files

Collections

Research