RDI-SD: An Efficient Rice Disease Identification based on Apache Spark and Deep Learning Technique

Early and accurate detection of diseases affecting rice plants may have devastating impacts on productivity, and early and accurate detection of these diseases is essential for mitigating their consequences. However, the current methods for diagnosing rice diseases are neither precise nor effective. When it comes to diagnosing plant diseases, convolutional neural networks (CNNs) are the gold standard. The difficulty of using CNN for large-scale data analysis using conventional methods remains a major barrier to its wider adoption. In our work for massive data processing, we have adapted the CNN technique for use with pySpark. We used a dataset of 3,472 images of rice diseases to train and evaluate our suggested system. The proposed system will provide a tailored answer to the challenge of assessing rice diseases by employing smartphone plant images as its major data source. With the proposed model for identifying different rice diseases, a total accuracy of 99% was reached, which is pretty impressive given that some of the diseases look similar.