This research aims to use a deep neural network model for the accurate detection of rice plant disease. In order to facilitate this, it is necessary to collect and pre-process relevant data. This data will be used to train the model, which will ultimately be deployed for testing. To achieve the desired results, it is essential to evaluate and optimize the model’s performance in accordance with the collected data. For this, a VGG-16 based deep learning model will be built to classify and identify rice plant disease. Necessary data for this research would be collected and pre-processed in order to prepare it for the model’s training. The model will then be trained using this data, and its performance will be evaluated and optimized in accordance to the desired accuracy. Subsequently, the trained model will be tested on the collected data to accurately identify and classify rice plant disease. Overall, this research aims to use a VGG-16 based model for accurately identify and classify rice plant disease. It involves the collection and pre-processing of relevant data, training the model, and subsequent deployment for testing. The performance of the model will also be evaluated and optimized accordingly. If successful, this research should ultimately result in an accurate detection of rice plant disease.