What question did this study set out to answer?

This research aims to optimize deep learning models for accurate classification of Tricholoma species, while integrating explainable artificial intelligence features.

May 3, 2026Open Access

Optimization of deep learning models and applications of explainable artificial intelligence classification in some Tricholoma species

Key Points

This research aims to optimize deep learning models for accurate classification of Tricholoma species, while integrating explainable artificial intelligence features.
Developed a classification framework using convolutional neural network architectures on six macrofungi species.
Employed models like DenseNet121 and EfficientNetV2-M, achieving high classification scores.
Utilized Grad-CAM for explainable AI visualizations to assess model focus on relevant features.
DenseNet121 achieved a 90% F1-score; EfficientNetV2-M reached 92% accuracy and precision.
AUC scores of 90% or higher were observed across several tested models, indicating strong classification capabilities.
Models that focused on biologically relevant features like cap and stem surfaces outperformed others, reducing misclassification rates.

Abstract

Abstract Macrofungi are vital to ecosystem stability and biodiversity conservation, yet traditional species identification methods often require expert input and are prone to error. This study proposes a deep learning-based classification framework for six macrofungi species using advanced convolutional neural network (CNN) architectures. Among the tested models, DenseNet121 achieved a 90% F1-score, while EfficientNetV2-M reached 92% accuracy and 92% precision. AUC scores of 90% or higher were observed for DenseNet, EfficientNet-B4, EfficientNetV2-M, and ShuffleNet, demonstrating robust classification capabilities. Importantly, this study pioneers the integration of explainable artificial intelligence (XAI) in macrofungi classification by employing Grad-CAM. These visualizations revealed that top-performing models focused on biologically relevant features such as the cap, stem, and spore surfaces, whereas less accurate models fixated on background areas, leading to misclassification. The results highlight the importance of dataset size and variability in model performance and underscore the broader applicability of deep learning models beyond macrofungi, including spore-level analysis, plant disease diagnostics, and agricultural classification tasks. By enhancing interpretability and accuracy, this research provides a novel and effective approach for automated fungal identification, contributing significantly to biodiversity monitoring and ecological research.

Bookmark

View Full Paper