This study explores the urgent need for improved disease management in Climbing Perch aquaculture, a critical component of sustainable agriculture, in light of the global emphasis on food security and environmental sustainability. Conventional approaches to disease management in this field are often reactive, labor-intensive, and imprecise, hindering timely and effective action. To address these challenges, our research introduces an innovative approach utilizing artificial intelligence (AI) and machine learning for a proactive, accurate, and efficient disease management system. We present the Climbing Perch Disease Detection and Classification System (CPDDCS), employing cutting-edge imaging and deep learning technologies to automate disease detection. This system uniquely combines non-population based differential evolution algorithms for optimizing the mix of image augmentation techniques, with population-based algorithms for integrating image segmentation and convolutional neural network (CNN) architectures. The integration with custom hardware leads to the Automated CPDDCS (A-CPDDCS), enabling the automatic identification of diseases and rapid alerting to fish health issues. Tested on two self-collected datasets comprising 620 images, our system outperformed existing methods like ResNet-50 and InceptionV3, showing improvements of 7.83 % and 7.46 % in accuracy, achieving a remarkable 97.61 % overall accuracy. Operational performance of the CPDDCS highlights its efficiency, with response times averaging 0.95 s, a processing capacity of 1200 images per hour, and 99.98 % system uptime. Additionally, the System Usability Scale (SUS) scored 95.81, indicating high user satisfaction and the system's effectiveness. This research not only showcases the potential of AI in enhancing Climbing Perch disease management but also underscores the broader applicability of AI in agriculture, advocating for policies and investments in AI-driven agricultural technologies to bolster sustainable food production and meet global food security and environmental objectives. Through optimizing disease management, this work contributes to sustainable aquaculture and sets a precedent for technology-led innovation in the food system.