A Convolution Neural Network with Skip Connections (CNNSC) approach for detecting micronutrients boron and iron deficiency in banana leaves

Abstract Banana plants require a precise balance of 16 essential nutrients to flourish, with micronutrients playing a pivotal role in smaller proportions than macronutrients. Insufficient micronutrient provision in Banana plants can impede growth, hinder flowering, and diminish fruit production. Precise identification of deficiencies is imperative for farmers aiming to cultivate nutrient-dense crops and enhance their yields. Micronutrients such as Boron contribute to hormone regulation, while Iron facilitates enzyme function, DNA synthesis, and overall metabolic processes in plants. Observable manifestations of Boron and Iron deficiencies on banana leaves are crucial indicators necessitating intervention. The present work proposes a novel deep learning methodology, employing a CNN model with Skip Connections (CNNSC), to detect Boron and Iron deficiencies in banana foliage. The CNNSC model, featuring thirteen layers, surpasses established architectures like VGG16, DenseNet, and Inception V3. Training the model on a specialized curated dataset comprising 11,000 nutrient-deficient images, with a split of 70% for training and 30% for testing, has yielded promising outcomes. Key performance metrics, encompassing accuracy, loss, precision, F1-score, recall, and the confusion matrix underscore the efficacy of the model, achieving an impressive accuracy rate of approximately 95%.