Plant Protect. Sci., X:X | DOI: 10.17221/15/2025-PPS

From images to insights: Using a convolutional neural network to improve powdery mildew severity detection in mungbeanOriginal Paper

Pitchakon Papan¹, Witsarut Chueakhunthod^1,4, Chanwit Kaewkasi², Wanploy Jinagool¹, Akkawat Tharapreuksapong³, Teerayoot Girdthai¹, Kanlayanee Sawangsalee¹, Piyada Alisha Tantasawat ORCID...¹

¹ School of Crop Production Technology, Institute of Agricultural Technology, Suranaree University of Technology, Nakhon Ratchasima, Thailand

² School of Computer Engineering, Institute of Engineering, Suranaree University of Technology, Nakhon Ratchasima, Thailand

³ Center for Scientific and Technological Equipment, Suranaree University of Technology, Nakhon Ratchasima, Thailan

⁴ Department of Horticulture, Faculty of Agriculture, Kasetsart University, Bangkok, Thailand

To efficiently identify powdery mildew (PM) severity in mungbean leaves, we developed a Convolutional Neural Network (CNN) approach and validated its effectiveness against human evaluation. We fine-tuned an EfficientNet-B3 pre-trained model, which, in our related studies, performed better than re-implemented Inception V3 models. The CNN was trained on 90% of the images (2 880) for training and 10% (320) for validation, with data augmentation applied using Python and TensorFlow. The model obtained 82.10% and 73.03% as training and validation accuracies after 14 epochs, respectively. Further analysis with an additional 15 datasets revealed PM disease indices ranging from 2.03 (resistance) to 6.45 (high susceptibility). The concordance between AI-predicted and human-assessed PM severity was 74.4% (adjusted R²: 72.4%), with an average root mean squared error (RMSE) of 0.854 and a mean absolute error (MAE) of 0.715, indicating moderate predictive error. Comparison of our developed AI-based application prototype on smartphones with expert evaluations yielded a strong correlation (r = 0.992**, R² = 0.984), suggesting that this tool can effectively estimate PM severity across mungbean cultivars. The application shows considerable promise, and further optimisation and strategic dissemination efforts will enhance its adoption among farmers. 

Keywords: Artificial intelligence; deep learning; EfficientNet-B3; machine learning; Vigna radiata (L.) R. Wilczek; visual observation

Received: February 2, 2025; Revised: January 8, 2026; Accepted: January 11, 2026; Prepublished online: June 9, 2026