Advancing Precision Agriculture: Leveraging YOLOv8 for Robust Deep Learning Enabled Crop Diseases Detection

Precision agriculture relies on the early detection and isolation of crop diseases, and this research details how the You Only Look Once, Version 8 (YOLOv8) algorithm was used for the PlantVillage dataset. This research looks at how Deep Learning (DL) and Computer Vision (CV) could streamline and improve the diagnostic process, a problem with conventional disease detection approaches. The YOLOv8 model is trained and evaluated using the PlantVillage dataset, which consists of high-resolution photos encompassing different classes of crops and diseases. It is found that YOLOv8 outperformed other popular Machine Learning (ML) models in identifying agricultural diseases with 95% accuracy, 90% precision, 95% recall, 92% F1 score, and 90% specificity. Parameter optimization, advanced network architectures, and integration of the Internet of Things (IoT) and drones for real-time disease monitoring are just some of the future research directions proposed in this study, along with discussions of the difficulties posed by data availability, computational complexity, and resource requirements. YOLOv8's successful application to the PlantVillage dataset demonstrates its potential to automate and improve crop disease diagnosis, leading to more effective and environmentally friendly farming methods.