Year: 2026
Type: dissertation
Abstract: The study explores the design and execution viability of deep learning algorithms to the automated system of identifying plant diseases using leaf images.The global agricultural sector is experiencing significant losses in crop production due to late or inappropriate diagnosis of diseases caused by diseases especially in areas that lack agronomic knowledge.Four convolutional neural network architectures were tested to reduce such a problem: one of my own baseline CNN, ResNet-50, Inception-v3, and EfficientNet-B0.Training of the models was done using the PlantVillage dataset with the help of transfer learning, data augmentation, and routine preprocessing operations.The model performance was measured based on the accuracy, the precision, the recall, the F1score and ROC-AUC.Robustness testing was done by the introduction of synthetic noise, changes in light, and background complexity to simulate conditions in the realworld field.Grad-CAM visualisations were also added to increase the clarity and transparency of the model decisions.With empirical findings, it has been shown that EfficientNet-B0 gives an optimal trade-off between classification accuracy and computational efficiency, making it suitable to be deployed on a mobile or edge platform.The research offers practical results to the scalable, explainable, and resourceefficient implementation of artificial intelligence systems in the area of disease management in agriculture.
Author: Butt, Muhammad
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: green
OpenAlex ID: W7215477915