A Comparative Analysis of Classification Algorithms for Hyperspectral Data in Plant Stress Detection

The optimal condition of crops is of utmost significance in the field of Agriculture, as it ensures high crop yield to guarantee food security for future generations and sustained crop growth. Ensuring the well-being of crops is influenced and must be safeguarded through proactive measures, with early detection of plant stress being crucial. As a result, new technologies are emerging for the purpose of monitoring plant health. By leveraging cutting-edge technologies, we can preserve crops for future use, resulting in increased productivity and the ability to sustainably manage resources. This paper presents a succinct summary of the existing research on crop stress monitoring and the progress made in the technologies employed for early detection of stress or diseases. Furthermore, the plant images that have been impacted are captured and subjected to rigorous evaluation for stress analysis. The models employed for this purpose are then compared with those used in recent research studies. The paper also explores the various models and provides valuable insights into their applications in the field of agriculture. The research findings are subjected to further analysis and the identified stress methods are compared. The reader can acquire knowledge regarding the robustness and constraints of different models, as well as gain insights on selecting an appropriate model and conducting effective research.