A Lightweight and Erudite VGG 16+ResNet 50 Based Deep Learning Architecture Model for Enhanced Plant Yield Production

Preliminary detection of plant foliage diseases and classification can reduce the need for expensive agricultural procedures and help increase food production for farmers. Disease control and age prediction is therefore crucial for the development of agriculture, and it may be effectively carried out through early detection of plant diseases, which is necessary for timely usage of pesticides and control of diseases. Farmers often check for plant leaf diseases with their unaided vision, which is labor-intensive, prone to error, and can result in substantial losses in yield if predictions are incorrect. Several researchers use visual analysis and artificial intelligence approaches to efficiently handle this procedure. In order to address the shortcomings of human processing and the low recognition rate of other machine learning, statistical, and other methods, this work introduces a unique idea for identification of diseases in plants and age prediction by employing the hybrid model VGG16+ResNet 50 model. The class of diseases from various plant leaves can be recognized and categorized by the suggested VGG16+ResNet 50 model. Given that the two most current deep learning architectures are ResNet 50 and VGG16. The suggested work aims to integrate these two methodologies to design a hybrid architectural prototype for successful plant foliage disease identification, given their improved prediction performance and degree of accuracy. Adopting this hybridized methodology has the distinct advantage of accurately identifying the class of leaf disease from leaves of various plants, including fruits and vegetables. Performance evaluation is conducted using a variety of widely used open-source datasets and assessment metrics to test and validate the efficacy of the advanced hybrid architecture.