An enhanced AlexNet deep learning model integrated with Coordinate and Hybrid Channel-spatial attention achieves an average test accuracy of 99.62 percent in recognizing tomato leaf diseases, according to research published in Plant Cell Reports. Developed by a research team including Laixiang Xu, Yan Li, Madineh Bijani, Longguo Wu, Yanyan Zhang, and Junmin Zhao, the system addresses the operational demands of commercial tomato cultivation by offering automated disease diagnosis.
To build the model, the researchers modified the classical AlexNet framework to reduce computational overhead. The architecture was streamlined specifically to suit the characteristics of tomato leaf disease imagery, establishing a lightweight baseline intended for practical agricultural deployment.
The network design introduces two targeted attention mechanisms at distinct processing stages. A coordinate attention module was placed after the first and third convolutional layers to enhance the spatial localization of lesion areas on affected leaves. In addition, a hybrid channel-spatial attention module was incorporated following the second and fourth convolutional layers to strengthen discriminative feature learning across channels.
During experimental testing, the integrated approach achieved an average test accuracy of 99.62 percent, outperforming established deep learning networks including MobileNetV3 and ResNet50. The authors report that the model provides an effective and computationally efficient tool for automated disease monitoring in tomato production systems.
Subject of Research: Deep learning models for tomato leaf disease recognition
Article Title: ACHC: a novel deep learning model for tomato leaf disease
Article References: Xu, L., Li, Y., Bijani, M., Wu, L., Zhang, Y., & Zhao, J. (2026). ACHC: a novel deep learning model for tomato leaf disease. Plant Cell Reports, 45(12), Article 357. https://doi.org/10.1007/s00299-026-04038-7
Image Credits: AI Generated
DOI: 10.1007/s00299-026-04038-7
Keywords: deep learning, AlexNet, tomato cultivation, plant pathology, leaf disease, computer vision, coordinate attention, agricultural technology, ACHC, novel, deep, learning
News Source: Blake Davidson. (November 9, 2026). Enhanced AlexNet Model Improves Accuracy in Detecting Tomato Leaf Diseases. Scienmag.
