Automating yellow rust disease identification in wheat using artificial intelligence

Abstract

Plant disease has long been one of the major threats to world food security due to a reduction in crop yield and quality. Accurate and precise diagnosis of plant diseases has been a significant challenge. Cost-effective automated computational systems for disease diagnosis would facilitate advancements in agriculture. The objective of this paper is to explore a computer vision-based Artificial Intelligence method for automating the identification of yellow rust disease and improving the accuracy of plant disease identification. The dataset of 2000 images of wheat leaf was collected in the real-life experimental conditions of ICAR-Indian Agricultural Research Institute, New Delhi in the crop season during January-April, 2019. Based on our experiment, we propose a deep learning-based approach to detect healthy leaves and yellow rust-infected leaves in the wheat crop. The experiments are implemented in python with PyCharm IDE, utilizing the Keras deep learning library backend with TensorFlow. The proposed model achieves 97.3% testing accuracy and 98.42% training accuracy. The accuracy of the developed model can be improved further by training it with a larger size of dataset in the future. In the future, the accuracy of computer vision-based AI models can be improved by using larger size training datasets. Also, these models can be used for providing automatic advisory services to the farmers, thereby, adding much-needed assistance to the overloaded extension experts.