Detection of Water Stress in Vegetable Crops Using Deep Learning

DOI

10.2991/978-94-6463-587-4_47How to use a DOI?

Keywords

Image Classification; Machine Learning; Wilt Detection

Abstract

Properly monitoring plant health in hydroponic farming is crucial as the plants rely solely on mineral water flowing through their roots as a growth source. One of the main challenges is the early detection of wilt in plants due to water stress. If not addressed promptly, water stress can lead to crop failure. One approach used to detect the plant wilting level is by applying deep learning technology. This paper presents a novel approach to data collection and classification in the context of vertical aeroponic agriculture. To effectively monitor the condition of crops within this setup, a custom data collection system using a simple robotic arm was developed. Images of bok choy crops were captured in both fresh and wilted conditions. The proposed deep learning model processes three-channel images with a resolution of 128×128 pixels. Results show that the proposed deep learning model achieved a high overall accuracy of 90% in distinguishing between fresh and wilted conditions. The model correctly classified 131 out of 138 fresh samples and 107 out of 125 wilted samples, resulting in only 25 misclassifications out of 263 total samples.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - I Nyoman Kusuma Wardana
AU  - I Wayan Aditya Suranata
AU  - I Wayan Raka Ardana
AU  - Dewa Ayu Indah Cahya Dewi
AU  - Komang Ayu Triana Indah
AU  - Setio Basuki
PY  - 2024
DA  - 2024/12/01
TI  - Detection of Water Stress in Vegetable Crops Using Deep Learning
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2024 (ICoSTAS-EAS 2024)
PB  - Atlantis Press
SP  - 414
EP  - 422
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-587-4_47
DO  - 10.2991/978-94-6463-587-4_47
ID  - Wardana2024
ER  -