Attention-enhanced residual autoencoder for NIR spectral feature extraction and classification of grain varieties

Accurate identification of grain cultivars is critical for improving crop yields, streamlining agricultural workflows, and ensuring global food security. Near-infrared (NIR) spectroscopy offers a rapid, non-destructive solution for grain classification. However, its effectiveness hinges on extractin...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports Vol. 15; no. 1; pp. 32750 - 18
Main Authors: Kabiso, Abel Chernet, Ko, Cheng-Hao
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 24.09.2025
Nature Publishing Group
Nature Portfolio
Subjects:
631/449
639/166
639/705
Agricultural practices
Attention mechanisms
Autoencoder
Barley
Classification
Crop yield
Cultivars
Data analysis
Datasets
Deep learning
Food security
Grain
Grain classification
Humanities and Social Sciences
Infrared spectroscopy
Machine learning
multidisciplinary
Neural networks
PCA
Performance evaluation
Portable NIR spectroscopy
Science
Science (multidisciplinary)
Smartphones
Sorghum
Spectrometers
Spectrum analysis
Wavelet transforms
Grain classification
Attention mechanisms
Autoencoder
Portable NIR spectroscopy
PCA
ISSN:2045-2322, 2045-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate identification of grain cultivars is critical for improving crop yields, streamlining agricultural workflows, and ensuring global food security. Near-infrared (NIR) spectroscopy offers a rapid, non-destructive solution for grain classification. However, its effectiveness hinges on extracting meaningful spectral features. We propose SpecFuseNet, an attention-enhanced residual autoencoder, as a lightweight deep learning model for extracting NIR spectral features and classifying grain varieties. The encoder integrates Fused Efficient Channel Attention (FusedECA) and a Spectral Residual Gate (SRG) to extract informative spectral features, while a mirrored decoder enables robust spectral reconstruction. This architecture supports both spectral reconstruction and cultivar classification, with robust performance and minimal complexity. We evaluated SpecFuseNet on three NIR datasets: barley (1,200 samples, 24 varieties), chickpea (950 samples, 19 varieties), and sorghum (500 samples, 10 varieties) using stratified 5-fold cross-validation. The model achieved classification accuracies of 89.72%, 96.14%, and 90.67%, respectively, outperforming PCA-based machine learning models (SVM, Random Forest, XGBoost) and deep learning baselines such as standard Autoencoder (AE) and Convolutional Sparse Autoencoder (CSAE). These results demonstrate SpecFuseNet’s potential as a fast, interpretable, and deployable solution for real-time classification in field-based and resource-limited settings, with a lightweight design that enables deployment on portable or smartphone-connected NIR spectrometers, supporting sustainable and precise agricultural practices.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-025-17676-w