AI-Driven Smart Hydroponic Monitoring System for Water Quality and Disease Prediction

DOI

10.2991/978-94-6239-697-5_9How to use a DOI?

Keywords

Hydroponic farming; smart agriculture; machine learning; deep learning; water quality monitoring; plant disease detection; MobileNetV2; precision agriculture

Abstract

Hydroponic farming is increasingly being adopted as a sustainable agricultural technique due to its efficient use of water and ability to support controlled environment agriculture. However, maintaining optimal nutrient solution conditions and detecting plant diseases remain critical challenges that can significantly affect crop productivity. This study proposes an AI-driven smart hydroponic monitoring system that integrates machine learning and deep learning techniques for water quality assessment and plant disease prediction.

Water quality classification is performed using machine learning models trained on a combined dataset consisting of hydroponic and aquaponic environmental measurements, including pH, electrical conductivity (EC), and temperature. Several classification algorithms, including Logistic Regression, Decision Tree, Random Forest, and Gradient Boosting, were evaluated to determine the most effective model for identifying safe and unsafe nutrient solution conditions. Experimental results show that the Gradient Boosting classifier achieved the best performance with an accuracy of 95.58% and a ROC-AUC score of 0.9909.

In addition, a deep learning model based on the MobileNetV2 architecture was employed for lettuce disease detection using a publicly available leaf image dataset. The trained model achieved a validation accuracy of 98.40% in distinguishing between healthy and unhealthy plant leaves. The proposed models were integrated into a web-based dashboard that enables users to monitor hydroponic conditions, perform image-based disease detection, and obtain prediction results with confidence scores. The results demonstrate that combining machine learning-based environmental monitoring with deep learning-based plant health assessment can provide an effective intelligent decision-support system for hydroponic farming. The proposed framework contributes toward improving crop management and enabling early detection of unfavorable growing conditions in controlled agricultural environments.

Copyright

© 2026 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  - Priyanka Kumari
AU  - Arjun Singh Rawat
AU  - Gunjan Gunjan
PY  - 2026
DA  - 2026/06/04
TI  - AI-Driven Smart Hydroponic Monitoring System for Water Quality and Disease Prediction
BT  - Proceedings of the Conference on Bridging Engineering Disciplines with AI and Machine Learning (BEDAIML 2026)
PB  - Atlantis Press
SP  - 84
EP  - 97
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-697-5_9
DO  - 10.2991/978-94-6239-697-5_9
ID  - Kumari2026
ER  -