Paddy crop diseases can have a significant impact on crop production and food security, affecting farmers’ revenue, crop quality, and nearby crops’ health. Machine learning can assist farmers in preventing crop losses by providing early diagnosis and prediction of paddy crop diseases. The proposed framework uses the technology of AutoML to create a predictive model that accurately detects the presence of paddy crop diseases based on a variety of input data, including paddy crop images. The explainable AI (XAI) techniques incorporated in the framework enable a better understanding of the model’s working process and highlight the relevant parts of the image on which the model has been working. Furthermore, an API service is developed to make the framework more accessible and practical for research and farmer support applications. The framework’s efficacy is demonstrated by the high degree of accuracy in predicting the presence of paddy crop diseases, and its potential to benefit farmers by enabling them to take precautionary measures to reduce losses is discussed.
CITATION STYLE
Sowmiyan, L., Vaidya, S., & Karpagam, G. R. (2024). An Explainable AI (XAI)-Based Framework for Detecting Diseases in Paddy Crops. In Lecture Notes in Networks and Systems (Vol. 820, pp. 411–430). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-7817-5_31
Mendeley helps you to discover research relevant for your work.