Crop Monitoring & Disease Detection

Pest proliferation, population growth, and climate change are all still having an adverse effect on agricultural productivity. Both sustainable farming practices and food security depend on careful crop monitoring and early disease detection. This paper summarizes the literature that illustrates how modern technology and methods, like remote sensing, image processing, and machine learning, are used in the field of crop monitoring and disease diagnostics. We examine the advantages, disadvantages, and application of these methods in the modern world. We also talk about upcoming trends and offer a versatile, AI-assisted strategy to advance precision farming. This paper provides a comprehensive overview of contemporary techniques and systems for crop monitoring and disease detection. It explores satellite imaging, unmanned aerial vehicles (UAVs), sensor networks, and deep learning algorithms that collectively enable precision agriculture. Challenges, limitations, and future directions are also discussed. With the objective of highlighting the potential of federated learning in crop disease classification, among the CNN models tested, ResNet50 performed better in several experiments than the other models, and proved to be an optimal choice, but also the most suitable for a federated learning scenario.