Hybrid Machine Learning Model for Predicting Damage Scale in Sunflower Leaves affected by Aster Yellow Disease

Through this work a thorough summary of a predictive model specifically designed to evaluate Aster Yellows infections in sunflower leaves is presented. Exhibiting remarkable accuracy are the model's performance measures, which span from 97.74% to 97.89% for various Damage Scale categories and include precision, recall, and F1-Score. These measurements demonstrate how well the model performs in accurately categorizing cases within each group and highlight how consistently it measures the severity of Aster Yellows disease. The support values clarify the significant representation of cases on every Damage Scale, demonstrating the model's resilience to a variety of situations. This work trains and evaluates the model using the 6880-picture dataset, yielding an astonishing 97.81% overall accuracy, recorded repeatedly at 97.82% on average due to the high averages (of macro, weighted, or micro numbers within each kind). It not only shows high performance across the dataset but also its consistency across Damaged Scales is further supported. And not just the model's reliability, modest variations in support rates also increase its dependability: highlighting its capacity to manage multiple diverse Aster Yellows infection scenarios. Through the model, they can clearly distinguish between different levels of damage with an accuracy of 99 percent overall, which betokens its potential application in precision farming. Now, thanks to these compelling test numbers, farmers and agricultural experts will no longer have to guess at how to distinguish and treat sunflower plants suffering from Aster Yellows infection. In summary: The abstract deftly depicts this model's quantitative performance, general versatility, and possible pragmatic utility, making it a bright spot in the history of precision farming.