Classification of Macronutrient Deficiencies in Melon Leaves Using Convolutional Neural Networks

Abstract

Macronutrient deficiencies such as calcium, nitrogen, and potassium shortages in melon plants can significantly reduce harvest quality and productivity. This study aims to develop a classification model for detecting macronutrient deficiencies in melon leaves using Convolutional Neural Network (CNN). The dataset consists of 200 melon leaf images categorized into calcium deficiency, nitrogen deficiency, potassium deficiency, and healthy leaves. Data augmentation techniques were applied to enhance dataset variation, and the model was trained using Google Colab with GPU support. The CNN architecture includes convolutional layers for feature extraction, pooling layers for dimensionality reduction, dropout layers to prevent overfitting, and fully connected layers for classification. The model achieved high accuracy in classifying melon leaf conditions, demonstrating its potential as an effective tool for early detection of nutrient deficiencies. This research contributes to agricultural technology by providing an automated, accurate, and efficient method for diagnosing plant nutritional problems, enabling farmers to take timely preventive actions to improve crop yield and quality.