Deep Learning Model for Plant Disease Detection and Classification with Pesticide Suggestion

The development of an economy’s agricultural sector is directly proportionate to the growth of that economy’s potential for innovation, which in turn is directly related to the progress of that agricultural sector. The primary purpose of this investigation is to apply deep learning models to the process of constructing Plant Disease Detection and Classification Networks (PDDC-Net). The preprocessing step also involves the elimination of various kinds of noise, which ultimately leads to the standardization of the pictures that are a part of the dataset. In addition, the PDDC-Net puts the operation into practice by using a residual network based convolutional neural network (ResNet-CNN) for the purpose of feature extraction and classification. This work not only performs disease detection, but also performs pesticide suggestion, which is mostly helpful to farmers as well as e-agriculture applications. This allows the operation to be carried out more effectively. This contributes to ensuring that the operation is carried out correctly. The PDDCNet model that was suggested obtained an accuracy rate that was adequate for the detection and classification of plant leaf diseases, as shown by the outcomes of the tests that were carried out.