Innovative Solutions for Crop Health: A Hybrid Approach to Cotton Root Rot Severity Assessment

The proposed study aims to enhance our comprehension and control of the gravity of cotton root rot by integrating agricultural practices with technological advancements. The combination of a CNN, which possesses knowledge, with an SVM greatly enhances its ability to detect root rot. It possesses great strength, exhibits high adaptability, and demonstrates exceptional speed in task execution. The test results indicate that Cotton, a significant component of global agriculture, is currently confronted with a persistent issue caused by detrimental root rot. The cause of this issue is Phymatotrichopsis omnivora, which has the potential to negatively impact productivity if not well managed. Effectively managing illnesses relies on meticulous and prompt attention to the severity of root rot. Executing this challenging undertaking requires innovative concepts to achieve success. This study used a mixed model as a response. The method combines the properties of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) to develop a sophisticated approach for quantifying the severity of cotton root rot infections. Our inquiry starts with a substantial collection of 9,000 dispersed photographs. These high-resolution photographs depict the several manifestations of root rot in plants in proximity. Demonstrating the effectiveness of our blend model, we present a comprehensive accuracy rate of 98.56%. This demonstrates its proficiency in providing accurate and comprehensive threat assessments. The model's accuracy, memory recall, and F1 score serve as indicators of its performance.