An explainable hybrid feature aggregation network with residual inception positional encoding attention and EfficientNet for cassava leaf disease classification

Abstract Cassava is a tuberous edible plant native to the American tropics and is essential for its versatile applications including cassava flour, bread, tapioca, and laundry starch. Cassava leaf diseases reduce crop yields, elevate production costs, and disrupt market stability. This places signif...

Full description

Saved in:
Bibliographic Details
Main Authors: M. Sundara Srivathsan, S. Alden Jenish, K. Arvindhan, R. Karthik
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-95985-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850265577098051584
author M. Sundara Srivathsan
S. Alden Jenish
K. Arvindhan
R. Karthik
author_facet M. Sundara Srivathsan
S. Alden Jenish
K. Arvindhan
R. Karthik
author_sort M. Sundara Srivathsan
collection DOAJ
description Abstract Cassava is a tuberous edible plant native to the American tropics and is essential for its versatile applications including cassava flour, bread, tapioca, and laundry starch. Cassava leaf diseases reduce crop yields, elevate production costs, and disrupt market stability. This places significant burdens on farmers and economies while highlighting the need for effective management strategies. Traditional methods of manual disease diagnosis are costly, labor-intensive, and time-consuming. This research aims to address the challenge of accurate disease classification by overcoming the limitations of existing methods, which encounter difficulties with the complexity and variability of leaf disease symptoms. To the best of our knowledge, this is the first study to propose a novel dual-track feature aggregation architecture that integrates the Residual Inception Positional Encoding Attention (RIPEA) Network with EfficientNet for the classification of cassava leaf diseases. The proposed model employs a dual-track feature aggregation architecture which integrates the RIPEA Network with EfficientNet. The RIPEA track extracts significant features by leveraging residual connections for preserving gradients and uses multi-scale feature fusion for combining fine-grained details with broader patterns. It also incorporates Coordinate and Mixed Attention mechanisms which focus on cross-channel and long-range dependencies. The extracted features from both tracks are aggregated for classification. Furthermore, it incorporates an image augmentation method and a cosine decay learning rate schedule to improve model training. This improves the ability of the model to accurately differentiate between Cassava Bacterial Blight (CBB), Brown Streak Disease (CBSD), Green Mottle (CGM), Mosaic Disease (CMD), and healthy leaves, addressing both local textures and global structures. Additionally, to enhance the interpretability of the model, we apply Grad-CAM to provide visual explanations for the model’s decision-making process, helping to understand which regions of the leaf images contribute to the classification results. The proposed network achieved a classification accuracy of 93.06%.
format Article
id doaj-art-ea837a3b43134d09b05b74cd2fc13e4b
institution OA Journals
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ea837a3b43134d09b05b74cd2fc13e4b2025-08-20T01:54:23ZengNature PortfolioScientific Reports2045-23222025-04-0115111610.1038/s41598-025-95985-wAn explainable hybrid feature aggregation network with residual inception positional encoding attention and EfficientNet for cassava leaf disease classificationM. Sundara Srivathsan0S. Alden Jenish1K. Arvindhan2R. Karthik3School of Electronics Engineering, Vellore Institute of TechnologySchool of Electronics Engineering, Vellore Institute of TechnologySchool of Electronics Engineering, Vellore Institute of TechnologyCentre for Cyber Physical Systems, Vellore Institute of TechnologyAbstract Cassava is a tuberous edible plant native to the American tropics and is essential for its versatile applications including cassava flour, bread, tapioca, and laundry starch. Cassava leaf diseases reduce crop yields, elevate production costs, and disrupt market stability. This places significant burdens on farmers and economies while highlighting the need for effective management strategies. Traditional methods of manual disease diagnosis are costly, labor-intensive, and time-consuming. This research aims to address the challenge of accurate disease classification by overcoming the limitations of existing methods, which encounter difficulties with the complexity and variability of leaf disease symptoms. To the best of our knowledge, this is the first study to propose a novel dual-track feature aggregation architecture that integrates the Residual Inception Positional Encoding Attention (RIPEA) Network with EfficientNet for the classification of cassava leaf diseases. The proposed model employs a dual-track feature aggregation architecture which integrates the RIPEA Network with EfficientNet. The RIPEA track extracts significant features by leveraging residual connections for preserving gradients and uses multi-scale feature fusion for combining fine-grained details with broader patterns. It also incorporates Coordinate and Mixed Attention mechanisms which focus on cross-channel and long-range dependencies. The extracted features from both tracks are aggregated for classification. Furthermore, it incorporates an image augmentation method and a cosine decay learning rate schedule to improve model training. This improves the ability of the model to accurately differentiate between Cassava Bacterial Blight (CBB), Brown Streak Disease (CBSD), Green Mottle (CGM), Mosaic Disease (CMD), and healthy leaves, addressing both local textures and global structures. Additionally, to enhance the interpretability of the model, we apply Grad-CAM to provide visual explanations for the model’s decision-making process, helping to understand which regions of the leaf images contribute to the classification results. The proposed network achieved a classification accuracy of 93.06%.https://doi.org/10.1038/s41598-025-95985-wCassava leaf diseaseExplainable AIDeep learningConvolutional neural networkImage classification
spellingShingle M. Sundara Srivathsan
S. Alden Jenish
K. Arvindhan
R. Karthik
An explainable hybrid feature aggregation network with residual inception positional encoding attention and EfficientNet for cassava leaf disease classification
Scientific Reports
Cassava leaf disease
Explainable AI
Deep learning
Convolutional neural network
Image classification
title An explainable hybrid feature aggregation network with residual inception positional encoding attention and EfficientNet for cassava leaf disease classification
title_full An explainable hybrid feature aggregation network with residual inception positional encoding attention and EfficientNet for cassava leaf disease classification
title_fullStr An explainable hybrid feature aggregation network with residual inception positional encoding attention and EfficientNet for cassava leaf disease classification
title_full_unstemmed An explainable hybrid feature aggregation network with residual inception positional encoding attention and EfficientNet for cassava leaf disease classification
title_short An explainable hybrid feature aggregation network with residual inception positional encoding attention and EfficientNet for cassava leaf disease classification
title_sort explainable hybrid feature aggregation network with residual inception positional encoding attention and efficientnet for cassava leaf disease classification
topic Cassava leaf disease
Explainable AI
Deep learning
Convolutional neural network
Image classification
url https://doi.org/10.1038/s41598-025-95985-w
work_keys_str_mv AT msundarasrivathsan anexplainablehybridfeatureaggregationnetworkwithresidualinceptionpositionalencodingattentionandefficientnetforcassavaleafdiseaseclassification
AT saldenjenish anexplainablehybridfeatureaggregationnetworkwithresidualinceptionpositionalencodingattentionandefficientnetforcassavaleafdiseaseclassification
AT karvindhan anexplainablehybridfeatureaggregationnetworkwithresidualinceptionpositionalencodingattentionandefficientnetforcassavaleafdiseaseclassification
AT rkarthik anexplainablehybridfeatureaggregationnetworkwithresidualinceptionpositionalencodingattentionandefficientnetforcassavaleafdiseaseclassification
AT msundarasrivathsan explainablehybridfeatureaggregationnetworkwithresidualinceptionpositionalencodingattentionandefficientnetforcassavaleafdiseaseclassification
AT saldenjenish explainablehybridfeatureaggregationnetworkwithresidualinceptionpositionalencodingattentionandefficientnetforcassavaleafdiseaseclassification
AT karvindhan explainablehybridfeatureaggregationnetworkwithresidualinceptionpositionalencodingattentionandefficientnetforcassavaleafdiseaseclassification
AT rkarthik explainablehybridfeatureaggregationnetworkwithresidualinceptionpositionalencodingattentionandefficientnetforcassavaleafdiseaseclassification