Cereal Plants Classification and Disease Identification with Severity Scoring

As the world's primary food, cereal crops are vulnerable to a number of illnesses that can lower their quality and productivity. Previous illness indications and condition measurement require a lengthy and sometimes imprecise manual inspection. In this work, we present an artificial neural network for identification, classification and severity assessment of cereal plant diseases. This proposed technique uniquely employs CNNs in making diagnosis of diseases from pictures of plants as well as determining the intensity of the disease. We use a dataset with a variation of cereal plant diseases and include data on variations in symptoms and severity. The presented system design ideas emphasize on the use of advanced ML techniques with high accuracy at diagnosing diseases as well as determining their severity. In particular, we construct a severity scale to measure the advancement of disease and suggest possible treatments based on severity level. The proposed system provides more comprehensive solution for cereal plant disease that can diagnose the disease, the severity of the disease and the suggestion for treatment in short period and with high precision. The main objective of this study is to produce sustainable agriculture solutions by utilizing the advancements in automated agriculture.