Efficient multi-task CNN framework for joint identification of soybean leaf diseases and pesticide presence with explainable AI

Soybean production is significantly affected by crop diseases and improper pesticide use, which hinder effective disease management and reduce yield. In this study, we propose an efficient multi-task convolutional neural network (CNN) framework for the simultaneous detection of soybean seed diseases and pesticide presence from seed images. The model leverages a shared feature extraction backbone with task-specific output heads to learn complementary features for both disease classification and pesticide detection. A dataset of 429 soybean leaf images was preprocessed using normalization and augmentation techniques and split into training, validation, and testing sets. We evaluated three backbone architectures VGG19, MobileNetV3, and ConvNeXt within the multi-task framework. Experimental results demonstrate that the approach maintains computational efficiency suitable for real-world deployment while achieving high performance, with accuracies of 95%, 96%, and 97% for MobileNetV3, VGG19, and ConvNeXt, respectively. Additionally, explainable AI methods, such as Grad-CAM, highlight regions of focus for both tasks, making the model's decision-making process interpretable. This framework provides a practical tool for informed crop management and agricultural monitoring.