Advanced ABS Disease Recognition in Lemon-A Multi-Level Approach Using CNN and Random Forest Ensemble

This research presents a novel and powerful method for identifying lemon leaves infected with Alternate Brown Spot (ABS) by combining neural networks based on convolution (CNNs) and Random Forest (RF) algorithms. Citrus plantations are highly vulnerable to the destructive fungal disease ABS, which reduces yields and lowers fruit quality. To achieve multi-level recognition, the proposed model authors developed classifies lemon leaves into four groups: healthy, mildly diseased, severely infected, and severely sick. By fusing the feature extraction skills of CNNs with the accessibility of RF, this approach successfully combats ABS infection. The parameters of a convolutional neural network (CNN), which consists of three convolutional layers and a max-pooling layer, are optimized for feature extraction using training rates, activation functions, and kernel sizes. They also extensively compared many architectures to find the optimal CNN setup. To classify the levels of ABS infection in many images of lemon leaves, the RF file greatly increases the robustness and accuracy of the model. The combination of RF and CNN is an effective method for identifying ABS infections. The model's versatility is enhanced by the fact that this dataset covers a wide range of illnesses and disease stages. The multi-level recognition strategy allows agriculturalists and agronomists to make well-informed judgments on disease management, leading to more efficient and effective use of resources. The model's impressive accuracy in predicting the level of ABS infections in lemon leaves was validated by experiments, showing its promise as a useful resource for farmers. Finally, in light of growing threats to global food security, this innovative technique makes use of data-driven agriculture to advance sustainable practices and boost crop output. The methodology's flexibility and comprehensive assessment of CNN parameters help it combat the ABS infections problem and propel agricultural advances.