AI Model for Identification of Micro-Nutrient Deficiency in Banana Crop

Abstract

ABSTRACT: In order to detect vitamin deficiencies in banana crops, this project presents an advanced convolutional neural network (CNN) model that analyses leaf images. Proper nutrition is essential for optimal crop development and yield, and deficiencies in critical nutrients can have a detrimental impact on plant health and production. To address this problem, we have developed a bespoke CNN model that recognizes and classifies various nutrient deficits using detailed leaf pictures. The study used a sizable dataset of banana leaves with a variety of insufficiency indicators to train and evaluate the algorithm. The CNN architecture was carefully modified to enhance feature extraction and classification abilities and facilitate precise diagnosis of nutrient-related illnesses. The outcomes demonstrate the model's ability to distinguish between distinct nutrient deficiencies, which makes it a valuable tool for precision farming. This approach aims to improve nutrient management and crop health monitoring methods, highlighting the significant role that machine learning technology plays in advancing agricultural research and practices.

Code and data availability

The paper describes a CNN trained on banana leaf images for micronutrient deficiency classification, but provides no public dataset link, no code/model availability statement, and no repository identifier. The dataset is only described generically; the cited Data Brief banana deficiency dataset (ref 33) is prior work,

No evidence-backed public reproduction asset is currently recorded.