RoseGuard: Deep Learning-Based Classification of Rose Leaf Diseases for Precision Agriculture

This study presents an advanced Convolutional Neural Networks, model that has been specifically designed for the precise categorization of rose leaf diseases. The CNN model encompasses eight different classes. To tackle the complex problem of disease diagnosis, the architecture of the model, which consists of three convolutional layers, three max-pooling layers, and two fully linked layers, has been rigorously built. Using a dataset that is both broad and carefully curated, the model displays outstanding performance by reaching high precision, recall, and F1-Score values for each illness class. The fact that the model can make accurate predictions over a wide range of illness categories is demonstrated by the fact that it has an overall accuracy of 98%. The practical ramifications of this research extend beyond the areas of technical excellence to include rose farmers. It offers a dependable instrument for the early diagnosis of diseases and the focused intervention of those diseases. The findings highlight the potential of the deep learning approach that was presented to contribute to environmentally responsible agriculture practices and to reduce revenue losses in the flower business. Through the establishment of a solid platform for future breakthroughs in automated disease of plant identification, this research contributes to the ongoing transformation of precision agriculture brought about by technological advancements. In a nutshell, the CNN model that was constructed not only demonstrates a high level of technical expertise but also shows potential for improving agriculture sustainability and resilience in the context of rose leaves disease control.