AI summaryⓘ
The authors developed a computer program that uses images of peach leaves to identify different types of damage caused by stress, pests, or diseases. They created a large set of labeled images and tested several advanced AI models to see which could best recognize the different damage types. They found that models called EfficientNet, especially when combined with a technique named CBAM, performed the best at classifying leaf damage. The researchers also tested their approach on new images from local fields and showed that fine-tuning the models helped maintain high accuracy across different environments. Their work suggests AI can help automate and improve crop damage detection in varied conditions.
artificial intelligencecrop damage assessmentpeach leaf classificationdeep learningEfficientNetConvolutional Block Attention Moduletransfer learningdomain shiftmacro F1-score
Authors
Adrián Cánovas-Rodriguez, Miguel A. González-Illán, Maria Fernanda García-Cruz, Pedro Nortes Tortosa, José Salvador Rubio-Asensio, Miguel A. Zamora Izquierdo, Juan Antonio Martínez Navarro, Antonio F. Skarmeta
Abstract
Artificial intelligence provides a practical framework for crop damage assessment from imagery data, supporting early decision-making in agricultural management. In peach orchards, climate change increases abiotic stress and biotic pressures, including pests and diseases, which often produce visually similar foliar symptoms. This overlap makes manual diagnosis difficult, especially across multiple fields with varying environmental conditions, highlighting the need for automated models with strong generalization ability. We propose an image-based classification approach for peach leaf damage detection. A benchmark dataset was created through manual annotation of publicly available images, consisting of 1,366 peach leaves across six damage categories. Several deep learning architectures were evaluated. EfficientNet models achieved the best results, with EfficientNetB0 reaching 92.9 percent accuracy, EfficientNetB3 achieving 91.5 percent, and EfficientNetB5 showing the strongest performance on minority classes. DenseNet121 reached 92.6 percent accuracy. The integration of the Convolutional Block Attention Module (CBAM) improved performance in several backbones, particularly EfficientNetB5 and InceptionV3, while showing limited or negative impact in others. The CBAM-enhanced EfficientNetB5 achieved the best overall accuracy of 93.3 percent. To evaluate robustness under realistic conditions, a local dataset of 180 images across four classes was collected, and transfer learning strategies were applied to address domain shift. Three fine-tuning strategies were tested. EfficientNetB3 combined with CBAM achieved the best performance in the local domain, reaching a 93 percent macro F1-score after transfer. Overall, attention-based models showed improved robustness for minority classes and better generalization across different field conditions.