Skip to content
Open access

Interpreting potato disease classification using explainable artificial intelligence

Sep 2026 · International Journal of Advances in Applied Sciences · Vol 15, pp. 1123 · 0 citations · 26 references

TL;DR

It is suggested that explanation effectiveness is influenced by model design and data characteristics, highlighting the need for careful selection of interpretability techniques in precision agriculture applications.

Abstract

Timely and accurate crop diseases detection is most important for ensuring global food security. For detecting diseases in crops, many different machine learning (ML) models were proposed. These models work as a black-box, and without proper explanation of these models’ decisions, farmers may find it difficult to trust these systems. For this, many model explainability methods were also proposed. All these methods have been evaluated qualitatively, but their quantitative and cross-comparison are missing. This study addresses this gap by emphasizing quantitative validation of models’ explanations. This study investigates the interpretability and performance of two approaches for potato leaf disease classification: i) manual feature engineering with relief-based feature selection and artificial neural network (ANN) classification with local interpretable model-agnostic explanations (LIME) and ii) deep convolutional neural networks (CNNs) based on mobile network version 2 (MobileNetV2) with gradient-weighted class activation mapping (Grad-CAM). Quantitative assessment of explanation quality was performed using fidelity and robustness metrics. While LIME achieved a lower average fidelity drop 10.90% and higher robustness 84.27% compared to Grad-CAM 18.68% fidelity drops and 79.38% robustness, Grad-CAM provided clearer visual explanations. These findings suggest that explanation effectiveness is influenced by model design and data characteristics, highlighting the need for careful selection of interpretability techniques in precision agriculture applications.

Read PDF

Similar papers

#large language models Open access Oct 2026

Multi-Crop Leaf Disease Detection with LLM-Assisted Diagnosis and Explainable AI

Early identification of plant diseases is crucial for maintaining agricultural productivity and ensuring food security. Manually inspecting crop leaves takes a lot of time and requires expertise, making automated disease detection systems very helpful. This paper presents a framework for detecting leaf diseases in mult...

B. Likitha · 0 citations
Conference Aug 2026

XAI-MaizeNet: An Explainable Deep Learning Framework for Transparent and Interpretable Maize Leaf Disease Detection and Classification

Early and precise diagnosis of maize leaf diseases is vital to reduce crop losses and to ensure sustainable farming production. Nevertheless, traditional Deep Learning models are usually “black boxes,” making them unreliable and unpopular in real-world agricultural decision-making processes. To provide transparent and...

K. S. Kumar, Raveendrababu Vempati, J. Rahul · 0 citations
Open access Aug 2026

Deep Learning-Based Potato Leaf Disease Detection Using Transfer Learning and Explainable AI Techniques

This study improves potato leaf disease detection using a fine-tuned InceptionV3 with data augmentation and dropout, while Grad-CAM visualizations enhance model interpretability, reliability, and practical utility for accurate agricultural disease diagnosis.

Aradhy Tiwari, Amit Saxena, Chandrashekhar Chandrashekhar · 0 citations
Open access Sep 2026

Deep Learning-based Bean Leaf Disease Classification: A Comparison of ResNet50 and VGG19

This work demonstrates ResNet50’s performance for bean leaf disease classification tasks, providing important insights for future research and practical applications in agricultural disease control.

Yu-Yan Xu, H. Chen, Qing-Mei Lin · 0 citations
Open access Sep 2026

Efficient Tomato Leaf Disease Classification Using CNN

A deep learning–based framework is proposed for detecting and diagnosing plant diseases using images of healthy and infected leaves and suggests that the model is suitable for early disease detection and has the potential for further improvement toward real-world agricultural applications.

Zahraa Mohammed Taha Issa, H. Najm · 0 citations
Open access Sep 2026

Hybrid CNN-ViT framework for enhanced plant illness identification: accuracy and interpretability improvements

This research proposes a hybrid model for identifying plant (groundnut) illness status using a CNN and a vision transformer (HCVT), which outperformed current cutting-edge models in identifying plant disease and demonstrated its generalization potential.

Kummari Venkatesh, K. Naik · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.