Productivity in farming is very essential to the Indian economic system. When a plant gets any disease it can significantly reduce production, cost money and reduce the quality and quantity of farm produce. To prevent agriculture from losing quantity and quality, it is essential to recognise diseases of plants. Plant disease identification is receiving more and more attention these days since large crops area is being monitored. Monitoring plant health and identifying diseases is critical for sustainable agriculture. This requires a lot of work, knowledge of plant diseases, and a lot of processing time. Utilizing Machine Learning algorithms, To predict increased agricultural yields, crop yield projections are made. One of the difficult problems in the agricultural industry is this. Given the growing significance of agricultural yield prediction, with a concentrate on agricultural yield prediction, it is important to apply machine learning techniques to crop yield predictions. Techniques like decision tree, support vector machine, Bayesian Network, and random forest, among others, are used in Machine Learning support in the automatic identification of plant disease based on the plant’s visual symptoms. This research presents an analysis of several machine learning approaches for plant disease prediction. The outcomes demonstrate that this technique conducted illness diagnosis with success and enhanced diffusion pattern analysis and disease progression level detection accuracy. Thus machine learning approaches with special emphasis for identification of plant leaf diseases in crop yield prediction results show that plant diseases can be accurately classified.