Prediction of Nitrogen Deficiency in Paddy Leaves Using Convolutional Neural Network Model

At various stages of development, including flowering and fruit production, plants need a variety of minerals and nutrients to grow. The phenotype, quality, and yield of crops are all influenced by the nitrogen level in precision agriculture. In the future, it won’t be possible to achieve without the application of nitrogen fertilizer. A useful and cutting edge technique for diagnosing the nitrogen nutrition of crops is needed for an effective and appropriate nitrogen fertilizer management system. Plant diseases that have a substantial impact on agricultural output are brought on by nutrient deficiency. Rice producers can reduce output loss significantly by taking essential measures with the help of early disease identification. Deep learning, an effective machine learning method, has recently demonstrated considerable potential in the task of classifying images. The convolutional neural network has been trained after classification of the affected leaf regions. In this study, the lack of nitrogen in the paddy crop was identified and predicted using leaf data. The model achieved 95% of accuracy for identifying nitrogen deficiency in leaves from available dataset.