Developing a Multi-Level Nitrogen Malnutrition Detection on Paddy Leaf Using YOLOv11

Authors

  • Muhammad Syahmi Said Omar Universiti Tun Hussein Onn Malaysia
  • Nik Shahidah Afifi Md Taujuddin Universiti Tun Hussein Onn Malaysia
  • Suhaila Sari Universiti Tun Hussein Onn Malaysia

Keywords:

Yolov11, Paddy Malnutrition, Nitrogen Detection, Leaf Colour Chart, Precision Agriculture

Abstract

This project focuses on developing a YOLOv11 deep learning model to classify leaf nitrogen levels to support efficient crop health monitoring in precision agriculture. A dataset of 6,000 annotated images, representing nitrogen levels 2 to 5 based on the Leaf Colour Chart (LCC), was split into training (80%), validation (10%), and testing (10%) sets. The model achieved peak stability and accuracy at Epoch 130. For practical field use, the model was deployed into an Android mobile application via TensorFlow Lite. Real-time testing showed detection accuracy of 86% for Level 5 and 74% for Level 2, while intermediate levels 3 and 4 achieved lower rates of 56% and 46% due to visual color similarities. These findings demonstrate that YOLOv11 is a reliable tool for automated nutrient monitoring.

Downloads

Download data is not yet available.

Downloads

Published

22-06-2026

Issue

Vol. 7 No. 1 (2026): EEEE

Section

Computer and Network

How to Cite

Said Omar, M. S., Md Taujuddin, N. S. A. ., & Sari, S. . (2026). Developing a Multi-Level Nitrogen Malnutrition Detection on Paddy Leaf Using YOLOv11. Evolution in Electrical and Electronic Engineering, 7(1), 147-153. https://publisher.uthm.edu.my/periodicals/index.php/eeee/article/view/23160