IoT-Based Smart Hydroponic System for Nutrient Management Using Predictive Machine Learning Algorithms

Hydroponics, an efficient cultivation method, benefits significantly from the precision and adaptability that Machine Learning (ML) algorithms can offer, along with the real-time monitoring facilitated by the devices using the Internet of Things (IoT). This study summarises the latest research and discusses how Machine Learning and the IoT work together, focusing on nutrient optimization, plant development, and resource efficiency. The critical subjects of the discussion are the use of Machine Learning algorithms, the function of IoT devices for real-time monitoring, communication protocols, scalability issues, and implementation. This article discusses the transformative amalgamation of the IoT and Machine Learning technologies within vegetable hydroponic systems for nutrition management. The system integrates an IoT-enabled hardware setup comprising sensors for pH, temperature, humidity, light, and TDS, placed at strategic positions in the hydroponic unit, with data collected every 15 minutes for ML-based analysis. The study utilized machine learning classifiers for tomato crops for over 121 days, measuring the parameters such as temperature, humidity, Total Dissolved Solids, potential of hydrogen (pH), and crop type. The research indicates benefits to crop output, resource efficiency, and sustainability based on the case studies and the analysis of results. The machine learning models introduced in this research were evaluated against contemporary studies, revealing an accuracy enhancement ranging from 1.17% to 5.25%, depending on the dataset and algorithm employed. The present study conducts a Comprehensive analysis involving machine learning algorithms, indicating that among all the models, Random Forest (RF), Gaussian Naive Bayes (GNB), and Gradient Boosting (GB) achieved an accuracy of 99.71, 99.71, and 99.42%, respectively, in the dataset by making stage-wise decisions. Compared with recent literature on Machine Learning, models achieved better performance, highlighting the study's strengths. The conclusion of this paper provides directions for further research and calls for more investigation into state-of-the-art machine learning approaches and scalable solutions for the resilient and sustainable future of hydroponic agriculture.