Advancing Sustainable Agriculture In Ksa Using Deep Learning-Driven Automated Pepper Leaf Disease Recognition Model

Food security is a national strategic plan for Saudi Arabia and a part of Saudi Vision 2030. Focusing on an increased area under production to reduce import dependency on foods and, ultimately, food security has led to higher domestic production of food crops. Pepper is cultivated worldwide, and several farmer’s subsistence depends on these crops. Unfortunately, due to lower pepper productivity, farmers involved in pepper cultivation face enormous losses caused by various pepper diseases. These losses can be avoided if the disease is detected timely and accurate. The time needed for the procedure and improper detection cannot help reduce the losses and cannot be released from the diseases. Deep learning (DL)-based automated techniques are one of the most computing techniques can be used in environmental modeling for detecting plant disease can provide promising outcomes to the users for acquiring higher accuracy within a shorter time for recognizing pepper diseases. This study designs an Automated Pepper Leaf Disease Recognition and Classification using Optimal Deep Learning (APLDRC-ODL) technique to improve sustainable agriculture in KSA. The purpose of the APLDRC-ODL technique is to enhance crop productivity and reduce crop losses in KSA via the detection of pepper leaf diseases. The APLDRC-ODL technique involves a multi-faceted approach comprising median filtering (MF)-based noise elimination and Otsu thresholding-based segmentation as a preprocessing step. At the same time, complex and intrinsic features can be generated by the utilization of the capsule network (CapsNet) model. Meanwhile, the African vulture fractals optimization algorithm (AVOA) can be applied for the optimal hyperparameter selection process. Lastly, an extreme learning machine (ELM) classifier is utilized for the detection and classification of pepper diseases. An extensive set of experiments is performed to highlight the efficiency of the APLDRC-ODL technique under the pepper leaf disease dataset. The simulation process of the APLDRC-ODL technique highlighted a superior value of 98.32% compared to existing models.