<p>Crop diseases have a major impact on global food security by causing significant reductions in agricultural yields. Traditional methods are often slow and expert-dependent, highlighting the need for a more efficient, automated, and precise approach to minimize economic losses for farmers and enhance production efficiency. Potato is a vital crop used globally in various cuisines, and blight disease in potato leaves is a major contributor to crop deterioration worldwide. Plant leaf diseases often arise due to abrupt climate changes, improper fertilization, and excessive use of nitrogen-based fertilizers. The proposed research work addresses the challenges in potato leaf disease detection by introducing a novel lightweight deep-learning model named ‘uvaNet’. In this model, max-pooling operations have been reduced by half compared to the convolution operations to minimize information loss during the down-sampling of feature map dimensions. Additionally, skip connections are incorporated to preserve important features, and variable-sized kernels are strategically chosen to ensure the model remains lightweight. The effectiveness of the proposed method for blight disease classification is demonstrated on a publicly accessible Plant Village dataset containing potato leaf images. The efficacy of the proposed blight disease classification model has been evaluated using potato leaves from the Plant Village dataset. The proposed method exhibited a remarkable accuracy of 99.31% compared to the state-of-the-art techniques. Furthermore, a web-based portal has been developed for farmers to address the need for real-time pesticide optimization. The portal allows farmers to upload images of potato leaves suspected of blight infection, enabling them to quickly receive classification results and customized pesticide recommendations in both Hindi and English. Hence, this approach promotes early intervention, supports sustainable agricultural production, and helps reduce crop losses across the agricultural supply chain.</p>