International Journal of Neutrosophic Science IJNS 2690-6805 2692-6148 10.54216/IJNS https://www.americaspg.com/journals/show/2944 2020 2020 Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia. Afef Afef Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, Kharj, Saudi Arabia. Samah Al Zanin Department of Computer and Self Development, Preparatory Year Deanship, Prince Sattam bin Abdulaziz University, AlKharj, Saudi Arabia Amani A. Alneil Unit of Scientific Research, Applied College, Qassim University, Buraydah, Saudi Arabia Imène Issaou Sustainable agriculture is of utmost importance in Saudi Arabia to resolve problems like environmental degradation and water scarcity. The country has made considerable investments in modern agricultural systems such as vertical farming and hydroponics to maximize crop yields and water efficiency. The most direct manifestation of earlier crop growth problems is Pepper leaf disease. Rapid and accurate detection of pepper leaf disease is crucial to immediately detect growth issues and enable accurate control and preventive measures. The traditional method based on human experience and visual inspection to recognize pepper leaves is costly, subjective and laborious. Hence, it is essential to develop fast, convenient, and precise techniques for identifying pepper leaf disease. The Q-neutrosophic soft relation is a generalization that integrates the concepts of soft set and neutrosophic set, enabling for truth, indeterminacy, and false degree in the membership of element with respect to a relation in a soft computing framework. Therefore, this study introduces a new Q Neutrosophic Soft Relation with Deep Learning based Pepper Leaf Disease Recognition (QNSRDL-PLDR) technique for Sustainable Agriculture in KSA. The proposed QNSRDL-PLDR method leverages DenseNet for feature extraction, the model uses the Adam optimizer for effective parameter optimization. Unique to this framework is the combination of a Q-neutrosophic soft relation classifier, allowing nuanced classification considering truth, indeterminacy, and falsity degrees in disease presence assessment. A comprehensive set of simulations is conducted to demonstrate the better efficiency of the QNSRDL-PLDR technique. This technique aims to improve reliability and accuracy in detecting Pepper Leaf Diseases, critical for crop management and sustainable agricultural practices 2025 2025 190 202 10.54216/IJNS.250117 https://www.americaspg.com/articleinfo/21/show/2944