<p>The study proposes a Hybrid AlexNet-ShuffleNet framework for plant leaf disorder identification. The investigational outcomes prove that the presented hybrid approach outperforms both AlexNet and ShuffleNet in terms of specificity, accuracy and sensitivity. The model offers practical applicability for farmers and plant disease researchers to detect and prevent crop losses caused by plant leaf diseases. The hybrid model proposed in the study combines the advantages of both AlexNet and ShuffleNet, resulting in improved accuracy compared to the individual networks. AlexNet excels in learning high-level features, while ShuffleNet specializes in reducing the computational difficulty of deep neural networks. The hybrid technique leverages these strengths with the RoI extracted to enhance the overall performance of the procedure. The projected scheme reached maximum accuracy rate of 95.09%, sensitivity rate of 97.98% and specificity rate of 93.93%. Overall, the hybrid framework has the potential to be a valuable tool for agricultural production in the recognition and prevention of plant leaf disorder.</p>