Advancements in Plant Leaf Disease Classification: Integrating Machine Learning and Graph Convolutional Networks for Sustainable Agriculture
Rahul Chiranjeevi, S. Dhanasekaran, م.م رواء عبد الأمير عباس, Senthil Pandi S
Abstract
In order to support life on Earth and preserve ecological equilibrium, plants are essential. However, a variety of biotic and abiotic elements constantly pose a threat to them; plant leaves are especially susceptible to illness. The ethology of plant leaf diseases, their consequences on plant health, and mitigation strategies are mined in this research. The categorization of plant leaf diseases both infectious and noninfectious the main topic of discussion. These illnesses threaten global foo d security and ecosystems because of their sensitivity to infections, the environment, and genetics. The significance of effective disease management is emphasized in the article, which takes into account elements like sustainable practices, data driven disease forecasting, and precision agriculture. The application of Artificial Intelligence (AI) and Machine Learning (ML) is touted as a potent technique for classifying plant leaf diseases. The proposed approach, which makes use of graph convolutional networks, offers a fresh way to get around current problems. The importance of high-quality datasets for creating precise decision support systems is covered in the study. It is emphasized how adaptable ML models are, enabling ongoing learning and the identification of novel illnesses. Notwithstanding the progress made, obstacles including class imbalance and massive data problems are recognized, highlighting the necessity of meticulous experimental planning and model training.