Predictive Modelling of Rice Blast Disease Utilizing Ensemble Voting Classifiers in Machine Learning

Rice is the second-most significant cereal plant, next to wheat, and the most commonly cultivated staple food in India. Rice production has declined in recent years due to the spread of several rice diseases, changes in weather conditions, and soil quality. Rice blast, also known as RB, is the most devastating of all rice plant diseases and causes a vast amount of annual loss. The key challenge is to minimize crop loss due to rice blast disease while also increasing agricultural output. It is critical to predict the disease ahead of time so that the required safeguards can be taken. As manual prediction of rice blast disease requires a huge amount of labor and time, it is a must to implement an automated system using machine learning (ML) techniques, which are widely used artificial intelligence (AI) methods for prediction models. In the proposed system, the sample data set of 15,400 has been fed as an input to the ML algorithms via Nïve Bayes, random forest, KNN, and voting classifiers for prediction. The results show that the ensemble method of combining the machine learning algorithm-based prediction technique offers improved accuracy than the random forest algorithm, with an accuracy of 99.5%. The proposed methodology will greatly benefit agriculturalists with increased profits and safeguard food for the country.