Enhancing Crop Resilience: A Deep Learning Framework for Timely Identification of Potato Leaf Diseases Through NLSCTAN and IoT Integration

Potato disease management is crucial to reducing significant crop losses in agriculture. The timely identification and classification of potato leaf diseases are necessary but time-consuming and labor-intensive. Therefore, an automated model capable of accurate and timely recognition and classification is key to resolving these challenges. In this research, a novel Normalized Long- Short Convoluted Temporal Attention Network (NLSCTAN) with Internet of Things (IOT) is developed to classify infected potato leaves and provide fertilizer suggestions to combat diseases. This work introduces a diverse dataset collected from IOT sensors by merging similar classes from three distinct potato leaf datasets: the potato leaf disease dataset, potato leaf diseases, and the plant village dataset. Preprocessing is performed using adaptive Contrast-Limited Adaptive Histogram Equalization (CLAHE) with double gamma correction to enhance the image quality. Feature extraction involves extracting different texture features using ternary patterns and discrete wavelet transform. Subsequently, dimensionality reduction is achieved through an auto encoder. Finally, the NLSCTAN model combines segmentation and classification processes to extract infected regions, determine their identity, and suggest appropriate fertilizers. Modified walrus optimization further enhances accuracy by minimizing the loss function of the neural network. The proposed procedure outperforms existing models, achieving a mean accuracy of 99.2% across various potato disease types. Experimental findings validate its competitiveness and effectiveness.