Rice Plant Health Analysis for Damage Severity Levels

The objective of this research is to examine whether a model for classifying things works by giving a detailed look at various phases of rice leaf impairment. It's vital to accurately analyze leaf health if you want to maximize harvests and pursue ethical farming. Its efficacy is assessed using precision, recall, and F1-score metrics for various stages of leaf deficits, from healthy states to severe deficits. With a total precision of 89.20%, the findings show excellent precision. Precision values between 86.12% and 91.31% show that the model can categorize positive events precisely. Recall ranges from 86.37% to 91.74%, showing efficient leaf damage detection. The model is capable of classifying different levels of rice leaf damage, as reflected by the F1-score, an even statistic combining precision and recall, which varies from 86.98% to 91.17%. These discoveries aid in precision farming by offering beneficial details for disease identification tools. A superior crop-handling approach is made possible by the model's accuracy in determining severity levels.