Cognitive Farming in Agriculture: Deploying CNN-RF for Maize Disease Precision Diagnostics

A hybrid approach integrating both CNN and RF is investigated in this research study of the Survey regarding the classification of maize leaf diseases with the help of CNN and RF. Our research carefully contrasts five created disease severities as a reported diagnostic tool for agriculturalists. The high accuracy of the model was extensively validated by applying various performance metrics with excellent precision of the different classes ranging from 95.90% to 98.47% for recall ranged between 95.01% to 99.21%, and F1- scores ranged between 96.55% to 98.4. The model achieved a general accuracy of 97.42851 %. We employed various averaging approaches to generalize the performance results across varying illness levels. A macro average yielded an accuracy of 97.37%, recall of 97.48%, and F1-score of 97.42%, implying similarity of performance across classes. Considering class imbalance, the weighted average was accurate at 97.44%, recalled at 97.43%, and the F1-score was similar at 97.43%. The micro average, as the aggregation of results across classes, was remarkably stable at 97.43 %, representing the performance of the model well and especially favoring frequent courses. Early identification and classification of diseases affecting maize leaves significantly contributed to precision agriculture, and this paper presents a reliable and efficient method for a timely diagnosis. It shows the stable performance of the CNN-RF model because many statistical measures are indicated. This implies that it possesses reasonable practicality in agricultural applications that highly support pest control and increase crop yields.