Agriculture is the country’s principal source of economic growth which also creates jobs, maintains food security, supplies raw materials for other industries, promotes rural development, supports international trade and has an impact on social and cultural norms, yet plant diseases and pests impact agricultural output and its quality. Pests and diseases of plants are a major threat to grape production, weakening economic stability, increasing costs and altering market conditions. Proper handling and oversight are essential for reducing these effects and guaranteeing the continued success of the production of grapes. Grapes give more financial support to our country, at the same time are susceptible to different types of ailments. Seven primary pests and illnesses generate considerable financial losses in the grape agriculture field. They are anthracnose, brown spot, mites, black rot, downy mildew, leaf blight and ESCA. These circumstances significantly diminish grapevine output. To stop this and sustain the grape sector’s healthy growth, leaf infections must be diagnosed and identified at an early stage. The goal is to apply CNNs for pinpointing and categorise diseases. To improve accuracy, we combine residual learning with the Deep Convolution Neural Network (DCNN) algorithm to detect and categorise hyperspectral images.