Antimicrobial Studies of Copper (II) Sesame Urea and Thiourea Complex Against Staphylococus Aureus

In this paper, an analysis of several machine learning and prediction techniques was conducted on 2,000 infected and healthy soybean plants to assess how these techniques can predict charcoal rot diseases. It is critical for agriculture to prevent the spread of disease by predicting pathogen infestations in advance. There are several causes of charcoal rot and among them are Macrophomina phaseolina (Tassi) Goid significantly lowers the productivity of the plants. Soybeans are at risk of a serious disease called charcoal rot. Traditional methods of disease prediction in soybeans are very time-consuming and not practical. There has been substantial interest in Machine Learning (ML) techniques across a variety of domains in recent years. Plant diseases can be detected by ML methods, even before symptoms appear fully. Inputs to ML models are a set of morphological and physiological features. Almost all of the machine learning models that have been developed achieved an accuracy of more than 90%. Among the methods used in this study, Graded Tree Boosting (GBT) achieved the best performance regarding sensitivity and specificity, with scores of 96.25 and 97.33% respectively. Based on our results, we were able to demonstrate that ML, specifically GBT, can be a successful tool for predicting the incidence of charcoal rot in real world situations. We also illustrated how it is crucial to incorporate physiological features into the learning process in order to ensure a successful outcome.