An important part of the agricultural industry is crop production. In particular, tainted crops are largely blamed for the food loss, which naturally slows down development. In the world of agriculture, it is quite challenging to detect plant diseases. It is now feasible to produce enough food to meet society’s demands thanks to modern technologies. But the security of the food and the harvests remained elusive. Numerous issues, such as plant disease, declining pollinators, and climate change, pose challenges for farmers. It is imperative to provide a solid foundation for these issues. The product’s assembly and the market’s economic value will both be severely harmed by inaccurate identification. This work aims at a novel approach to modelling and identification of plant disease progression through the categorization of leaf pictures and huge convolutional networks. To promote the program’s simple execution in observance, a novel technique and method were used. The suggested approach can distinguish thirteen different forms of plant illnesses from healthy leaves by differentiating between diseased and healthy leaves. Agricultural consultants took all the required actions, starting with gathering photos to add information, to incorporate this disease recognition model area unit that was depicted during the project. To do the deep CNN technique, we choose to use PyCham and Python.